BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Chao Xu

Chao Xu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
RoboticsComputer VisionMachine LearningArtificial IntelligenceInformation Theorymath.ITmath.OCComputation and Languagecond-mat.mes-hallcond-mat.str-elcond-mat.supr-conData Structures and Algorithmseess.IVeess.SPNetworking and Internet Architecturequant-phcs.CYDiscrete Mathematicsphysics.chem-phphysics.comp-phphysics.flu-dynphysics.geo-phSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
57works
0followers
23topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

57 published item(s)

preprint2026arXiv

Calibrated Surprise: An Information-Theoretic Account of Creative Quality

The essence of good creative writing is calibrated surprise: when constraints from all relevant dimensions act together, the feasible solution space collapses into a narrow region, and the surviving choices look least predictable from an unconstrained view. "Calibrated" has a precise meaning: the author's intent, the reader's reasonable expectation, and the logic of reality converge. When these three independent judgements agree on every dimension, the set of admissible writing choices is forced into a very small region. A mathematical corollary follows: full-dimensional accuracy and mediocrity are mutually exclusive -- two sides of one constraint structure, not separate goals. We use Shannon's mutual information $I(X;Y) = H(X) - H(X|Y)$ as our analysis tool. "Calibrated" corresponds to conditional entropy going to zero; "surprise" to entropy going up; mutual information is the precise measure of the joint quantity. The argument rests on two pillars. Static: when constraints from ethos, mythos, lexis, and dianoia are imposed together, the admissible set collapses sharply, and surviving solutions show up as low-probability choices from an unconstrained view. Dynamic: the chain rule shows each writing choice is constrained by what came before and constrains what comes after; macro-level decisions naturally contribute a larger share of information, removing the need for hand-tuned weighting. Through case studies and lightweight LLM-logprob computations, we show the framework is both analytically useful and operational, laying the theoretical groundwork for Creative Quality Alignment (CQA) and a professional evaluation benchmark.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation

Current state-of-the-art paradigms predominantly treat Text-to-Motion (T2M) generation as a direct translation problem, mapping symbolic language directly to continuous poses. While effective for simple actions, this System 1 approach faces a fundamental theoretical bottleneck we identify as the Semantic-Kinematic Impedance Mismatch: the inherent difficulty of grounding semantically dense, discrete linguistic intent into kinematically dense, high-frequency motion data in a single shot. In this paper, we argue that the solution lies in an architectural shift towards Latent System 2 Reasoning. Drawing inspiration from Hierarchical Motor Control in cognitive science, we propose Latent Motion Reasoning (LMR) that reformulates generation as a two-stage Think-then-Act decision process. Central to LMR is a novel Dual-Granularity Tokenizer that disentangles motion into two distinct manifolds: a compressed, semantically rich Reasoning Latent for planning global topology, and a high-frequency Execution Latent for preserving physical fidelity. By forcing the model to autoregressively reason (plan the coarse trajectory) before it moves (instantiates the frames), we effectively bridge the ineffability gap between language and physics. We demonstrate LMR's versatility by implementing it for two representative baselines: T2M-GPT (discrete) and MotionStreamer (continuous). Extensive experiments show that LMR yields non-trivial improvements in both semantic alignment and physical plausibility, validating that the optimal substrate for motion planning is not natural language, but a learned, motion-aligned concept space. Codes and demos can be found in \hyperlink{https://chenhaoqcdyq.github.io/LMR/}{https://chenhaoqcdyq.github.io/LMR/}

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

A Linear and Exact Algorithm for Whole-Body Collision Evaluation via Scale Optimization

Collision evaluation is of vital importance in various applications. However, existing methods are either cumbersome to calculate or have a gap with the actual value. In this paper, we propose a zero-gap whole-body collision evaluation which can be formulated as a low dimensional linear program. This evaluation can be solved analytically in O(m) computational time, where m is the total number of the linear inequalities in this linear program. Moreover, the proposed method is efficient in obtaining its gradient, making it easy to apply to optimization-based applications.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems

In this paper, we propose a novel nonlinear observer based on neural networks, called neural observer, for observation tasks of linear time-invariant (LTI) systems and uncertain nonlinear systems. In particular, the neural observer designed for uncertain systems is inspired by the active disturbance rejection control, which can measure the uncertainty in real-time. The stability analysis (e.g., exponential convergence rate) of LTI and uncertain nonlinear systems (involving neural observers) are presented and guaranteed, where it is shown that the observation problems can be solved only using the linear matrix inequalities (LMIs). Also, it is revealed that the observability and controllability of the system matrices are required to demonstrate the existence of solutions of LMIs. Finally, the effectiveness of neural observers is verified on three simulation cases, including the X-29A aircraft model, the nonlinear pendulum, and the four-wheel steering vehicle.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

PanGu-$π$: Enhancing Language Model Architectures via Nonlinearity Compensation

The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which is definitely proved by a lot of work such as the famous GPT and Llama. However, large models often involve massive computational costs, and practical applications cannot afford such high prices. However, the method of constructing a strong model architecture for LLMs is rarely discussed. We first analyze the state-of-the-art language model architectures and observe the feature collapse problem. Based on the theoretical analysis, we propose that the nonlinearity is also very important for language models, which is usually studied in convolutional neural networks for vision tasks. The series informed activation function is then introduced with tiny calculations that can be ignored, and an augmented shortcut is further used to enhance the model nonlinearity. We then demonstrate that the proposed approach is significantly effective for enhancing the model nonlinearity through carefully designed ablations; thus, we present a new efficient model architecture for establishing modern, namely, PanGu-$π$. Experiments are then conducted using the same dataset and training strategy to compare PanGu-$π$ with state-of-the-art LLMs. The results show that PanGu-$π$-7B can achieve a comparable performance to that of benchmarks with about 10\% inference speed-up, and PanGu-$π$-1B can achieve state-of-the-art performance in terms of accuracy and efficiency. In addition, we have deployed PanGu-$π$-7B in the high-value domains of finance and law, developing an LLM named YunShan for practical application. The results show that YunShan can surpass other models with similar scales on benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

An Image Patch is a Wave: Phase-Aware Vision MLP

In the field of computer vision, recent works show that a pure MLP architecture mainly stacked by fully-connected layers can achieve competing performance with CNN and transformer. An input image of vision MLP is usually split into multiple tokens (patches), while the existing MLP models directly aggregate them with fixed weights, neglecting the varying semantic information of tokens from different images. To dynamically aggregate tokens, we propose to represent each token as a wave function with two parts, amplitude and phase. Amplitude is the original feature and the phase term is a complex value changing according to the semantic contents of input images. Introducing the phase term can dynamically modulate the relationship between tokens and fixed weights in MLP. Based on the wave-like token representation, we establish a novel Wave-MLP architecture for vision tasks. Extensive experiments demonstrate that the proposed Wave-MLP is superior to the state-of-the-art MLP architectures on various vision tasks such as image classification, object detection and semantic segmentation. The source code is available at https://github.com/huawei-noah/CV-Backbones/tree/master/wavemlp_pytorch and https://gitee.com/mindspore/models/tree/master/research/cv/wave_mlp.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Automatic Evolution of Machine-Learning based Quantum Dynamics with Uncertainty Analysis

The machine learning approaches are applied in the dynamical simulation of open quantum systems. The long short-term memory recurrent neural network (LSTM-RNN) models are used to simulate the long-time quantum dynamics, which are built based on the key information of the short-time evolution. We employ various hyperparameter optimization methods, including the simulated annealing, Bayesian optimization with tree-structured parzen estimator and random search, to achieve the automatic construction and adjustment of the LSTM-RNN models. The implementation details of three hyperparameter optimization methods are examined, and among them the simulated annealing approach is strongly recommended due to its excellent performance. The uncertainties of the machine learning models are comprehensively analyzed by the combination of bootstrap sampling and Monte-Carlo dropout approaches, which give the prediction confidence of the LSTM-RNN models in the simulation of the open quantum dynamics. This work builds an effective machine learning approach to simulate the dynamics evolution of open quantum systems. In addition, the current study provides an efficient protocol to build the optimal neural networks and to estimate the trustiness of the machine learning models.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Automatic Parameter Adaptation for Quadrotor Trajectory Planning

Online trajectory planners enable quadrotors to safely and smoothly navigate in unknown cluttered environments. However, tuning parameters is challenging since modern planners have become too complex to mathematically model and predict their interaction with unstructured environments. This work takes humans out of the loop by proposing a planner parameter adaptation framework that formulates objectives into two complementary categories and optimizes them asynchronously. Objectives evaluated with and without trajectory execution are optimized using Bayesian Optimization (BayesOpt) and Particle Swarm Optimization (PSO), respectively. By combining two kinds of objectives, the total convergence rate of the black-box optimization is accelerated while the dimension of optimized parameters can be increased. Benchmark comparisons demonstrate its superior performance over other strategies. Tests with changing obstacle densities validate its real-time environment adaption, which is difficult for prior manual tuning. Real-world flights with different drone platforms, environments, and planners show the proposed framework's scalability and effectiveness.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Autonomous and Adaptive Navigation for Terrestrial-Aerial Bimodal Vehicles

Terrestrial-aerial bimodal vehicles bloom in both academia and industry because they incorporate both the high mobility of aerial vehicles and the long endurance of ground vehicles. In this work, we present an autonomous and adaptive navigation framework to bring complete autonomy to this class of vehicles. The framework mainly includes 1) a hierarchical motion planner that generates safe and low-power terrestrial-aerial trajectories in unknown environments and 2) a unified motion controller which dynamically adjusts energy consumption in terrestrial locomotion. Extensive real-world experiments and benchmark comparisons are conducted on a customized robot platform to validate the proposed framework's robustness and performance. During the tests, the robot safely traverses complex environments with terrestrial-aerial integrated mobility, and achieves $7\times$ energy savings in terrestrial locomotion. Finally, we will release our code and hardware configuration for the reference of the community.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Certifiably Optimal Mutual Localization with Anonymous Bearing Measurements

Mutual localization is essential for coordination and cooperation in multi-robot systems. Previous works have tackled this problem by assuming available correspondences between measurements and received odometry estimations, which are difficult to acquire, especially for unified robot teams. Furthermore, most local optimization methods ask for initial guesses and are sensitive to their quality. In this paper, we present a certifiably optimal algorithm that uses only anonymous bearing measurements to formulate a novel mixed-integer quadratically constrained quadratic problem (MIQCQP). Then, we relax the original nonconvex problem into a semidefinite programming (SDP) problem and obtain a certifiably global optimum using with off-the-shelf solvers. As a result, our method can determine bearing-pose correspondences and furthermore recover the initial relative poses between robots under a certain condition. We compare the performance with local optimization methods on extensive simulations under different noise levels to show our advantage in global optimality and robustness. Real-world experiments are conducted to show the practicality and robustness.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Counter-rotating spiral, zigzag, and 120$^\circ$ orders from coupled-chain analysis of Kitaev-Gamma-Heisenberg model, and relations to honeycomb iridates

We study the nearest neighboring spin-1/2 Kitaev-Heisenberg-Gamma ($KJΓ$) model on the honeycomb lattice in the parameter region of ferromagnetic (FM) Kitaev and antiferromagnetic (AFM) Heisenberg couplings relevant for honeycomb iridates, using a coupled-chain analysis. Starting from the gapless Luttinger liquid phase of a decoupled $KJΓ$ chain, the inter-chain interactions in the two-dimensional model is treated within a self-consistent mean field approach based on the Luttinger liquid theory. In the FM Gamma region, our analysis recovers the reported 120$^\circ$ magnetic order, previously obtained by classical analysis and exact diagonalization method. On the other hand, new physics is revealed in the AFM Gamma region, where three magnetic orders are found, including 120$^\circ$, commensurate counter-rotating spiral, and zigzag orders. Interestingly, the two first order phase transition lines separating these three magnetic orders merge at a single point at $K = -2 Γ$ and $J=0$, which is predicted to be a quantum critical point. The current theory captures the experimentally observed counter-rotating spiral order in $α$-Li$_22$IrO$_3$ and the zigzag order in Na$_2$IrO$_3$, thereby indicating that the spin-1/2 $KJΓ$ model may serve as a minimal model for honeycomb iridates. Limitations of the mean field theory presented in this work and the $J \rightarrow 0$ regime are also discussed.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Deep Learning Based Successive Interference Cancellation for the Non-Orthogonal Downlink

Non-orthogonal communications are expected to play a key role in future wireless systems. In downlink transmissions, the data symbols are broadcast from a base station to different users, which are superimposed with different power to facilitate high-integrity detection using successive interference cancellation (SIC). However, SIC requires accurate knowledge of both the channel model and channel state information (CSI), which may be difficult to acquire. We propose a deep learningaided SIC detector termed SICNet, which replaces the interference cancellation blocks of SIC by deep neural networks (DNNs). Explicitly, SICNet jointly trains its internal DNN-aided blocks for inferring the soft information representing the interfering symbols in a data-driven fashion, rather than using hard-decision decoders as in classical SIC. As a result, SICNet reliably detects the superimposed symbols in the downlink of non-orthogonal systems without requiring any prior knowledge of the channel model, while being less sensitive to CSI uncertainty than its model-based counterpart. SICNet is also robust to changes in the number of users and to their power allocation. Furthermore, SICNet learns to produce accurate soft outputs, which facilitates improved soft-input error correction decoding compared to model-based SIC. Finally, we propose an online training method for SICNet under block fading, which exploits the channel decoding for accurately recovering online data labels for retraining, hence, allowing it to smoothly track the fading envelope without requiring dedicated pilots. Our numerical results show that SICNet approaches the performance of classical SIC under perfect CSI, while outperforming it under realistic CSI uncertainty.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Detailed chemistry modelling of rotating detonations with dilute n-heptane sprays and preheated air

Utilization of liquid fuels is crucial to enabling commercialization of rotating detonation engines in the near future. In this study, Eulerian-Lagrangian simulations are conducted for rotating detonative combustion with dilute n-heptane sprays and preheated air. Two-dimensional flattened configuration is used and a skeletal chemical mechanism with 44 species and 112 elementary reactions for n-heptane combustion is adopted. The flow structure, droplet distribution, and thermochemical parameters in the refill zone are first analyzed. It is shown that the mixture in the refill zone is heterogeneous, including evaporating droplets, vapor, and air. When the total temperature is below 950 K, the average equivalence ratio increases with the total temperature. When it is higher than 950 K, the average equivalence ratio is almost constant. Subsequently, the chemical explosive mode analysis is applied to identify the controlling reactions and dominant combustion modes in the fuel refill zone and reaction fronts. Results demonstrate that the initiation reaction and low-temperature reaction are dominant in the upstream and downstream of the refill zone, respectively. The intermediate species from low-temperature chemistry is found to be important for the chemical explosive mode in the undetonated mixture. The influence of species diffusion and dispersed droplets is further analyzed. Results show that vapor autoignition facilitated by droplet evaporation occurs in the refill zone. Finally, the effects of the air total temperature on the detonation propagation speed and RDE propulsion performance are investigated. It is found that the detonation propagation speed and specific impulse increase with air total temperature.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Distributed Swarm Trajectory Optimization for Formation Flight in Dense Environments

For aerial swarms, navigation in a prescribed formation is widely practiced in various scenarios. However, the associated planning strategies typically lack the capability of avoiding obstacles in cluttered environments. To address this deficiency, we present an optimization-based method that ensures collision-free trajectory generation for formation flight. In this paper, a novel differentiable metric is proposed to quantify the overall similarity distance between formations. We then formulate this metric into an optimization framework, which achieves spatial-temporal planning using polynomial trajectories. Minimization over collision penalty is also incorporated into the framework, so that formation preservation and obstacle avoidance can be handled simultaneously. To validate the efficiency of our method, we conduct benchmark comparisons with other cutting-edge works. Integrated with an autonomous distributed aerial swarm system, the proposed method demonstrates its efficiency and robustness in real-world experiments with obstacle-rich surroundings. We will release the source code for the reference of the community.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Dynamic Free-Space Roadmap for Safe Quadrotor Motion Planning

Free-space-oriented roadmaps typically generate a series of convex geometric primitives, which constitute the safe region for motion planning. However, a static environment is assumed for this kind of roadmap. This assumption makes it unable to deal with dynamic obstacles and limits its applications. In this paper, we present a dynamic free-space roadmap, which provides feasible spaces and a navigation graph for safe quadrotor motion planning. Our roadmap is constructed by continuously seeding and extracting free regions in the environment. In order to adapt our map to environments with dynamic obstacles, we incrementally decompose the polyhedra intersecting with obstacles into obstacle-free regions, while the graph is also updated by our well-designed mechanism. Extensive simulations and real-world experiments demonstrate that our method is practically applicable and efficient.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Elastic Tracker: A Spatio-temporal Trajectory Planner Flexible Aerial Tracking

This paper proposes Elastic Tracker, a flexible trajectory planning framework that can deal with challenging tracking tasks with guaranteed safety and visibility. Firstly, an object detection and intension-free motion prediction method is designed. Then an occlusion-aware path finding method is proposed to provide a proper topology. A smart safe flight corridor generation strategy is designed with the guiding path. An analytical occlusion cost is evaluated. Finally, an effective trajectory optimization approach enables to generate a spatio-temporal optimal trajectory within the resultant flight corridor. Particular formulations are designed to guarantee both safety and visibility, with all the above requirements optimized jointly. The experimental results show that our method works more robustly but with less computation than the existing methods, even in some challenging tracking tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Federated Learning with Positive and Unlabeled Data

We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time. Different from the settings in traditional PU learning where the negative class consists of a single class, the negative samples which cannot be identified by a client in the federated setting may come from multiple classes which are unknown to the client. Therefore, existing PU learning methods can be hardly applied in this situation. To address this problem, we propose a novel framework, namely Federated learning with Positive and Unlabeled data (FedPU), to minimize the expected risk of multiple negative classes by leveraging the labeled data in other clients. We theoretically analyze the generalization bound of the proposed FedPU. Empirical experiments show that the FedPU can achieve much better performance than conventional supervised and semi-supervised federated learning methods. Code is available at https://github.com/littleSunlxy/FedPU-torch

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Generating Large-Scale Trajectories Efficiently using Double Descriptions of Polynomials

For quadrotor trajectory planning, describing a polynomial trajectory through coefficients and end-derivatives both enjoy their own convenience in energy minimization. We name them double descriptions of polynomial trajectories. The transformation between them, causing most of the inefficiency and instability, is formally analyzed in this paper. Leveraging its analytic structure, we design a linear-complexity scheme for both jerk/snap minimization and parameter gradient evaluation, which possesses efficiency, stability, flexibility, and scalability. With the help of our scheme, generating an energy optimal (minimum snap) trajectory only costs 1 $μs$ per piece at the scale up to 1,000,000 pieces. Moreover, generating large-scale energy-time optimal trajectories is also accelerated by an order of magnitude against conventional methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Geometrically Constrained Trajectory Optimization for Multicopters

We present an optimization-based framework for multicopter trajectory planning subject to geometrical configuration constraints and user-defined dynamic constraints. The basis of the framework is a novel trajectory representation built upon our novel optimality conditions for unconstrained control effort minimization. We design linear-complexity operations on this representation to conduct spatial-temporal deformation under various planning requirements. Smooth maps are utilized to exactly eliminate geometrical constraints in a lightweight fashion. A variety of state-input constraints are supported by the decoupling of dense constraint evaluation from sparse parameterization, and backward differentiation of flatness map. As a result, this framework transforms a generally constrained multicopter planning problem into an unconstrained optimization that can be solved reliably and efficiently. Our framework bridges the gaps among solution quality, planning efficiency, and constraint fidelity for a multicopter with limited resources and maneuvering capability. Its generality and robustness are both demonstrated by applications to different flight tasks. Extensive simulations and benchmarks are also conducted to show its capability of generating high-quality solutions while retaining the computation speed against other specialized methods by orders of magnitude. The source code of our framework is available at: https://github.com/ZJU-FAST-Lab/GCOPTER

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

GPA-Teleoperation: Gaze Enhanced Perception-aware Safe Assistive Aerial Teleoperation

Gaze is an intuitive and direct way to represent the intentions of an individual. However, when it comes to assistive aerial teleoperation which aims to perform operators' intention, rare attention has been paid to gaze. Existing methods obtain intention directly from the remote controller (RC) input, which is inaccurate, unstable, and unfriendly to non-professional operators. Further, most teleoperation works do not consider environment perception which is vital to guarantee safety. In this paper, we present GPA-Teleoperation, a gaze enhanced perception-aware assistive teleoperation framework, which addresses the above issues systematically. We capture the intention utilizing gaze information, and generate a topological path matching it. Then we refine the path into a safe and feasible trajectory which simultaneously enhances the perception awareness to the environment operators are interested in. Additionally, the proposed method is integrated into a customized quadrotor system. Extensive challenging indoor and outdoor real-world experiments and benchmark comparisons verify that the proposed system is reliable, robust and applicable to even unskilled users. We will release the source code of our system to benefit related researches.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ground and excited states of coupled exciton liquids in electron-hole quadrilayers

Interlayer excitons are bound states of electrons and holes confined in separate two-dimensional layers. Due to their repulsive dipolar interaction, interlayer excitons can form a correlated liquid. If another electron-hole bilayer is present, excitons from different bilayers can exhibit mutual attraction. We study such a quadrilayer system by a hypernetted chain formalism. We compute ground state energies, pair correlation functions, and collective mode velocities as functions of the exciton densities. We estimate the critical density for the transition to a paired biexciton phase. For a strongly unbalanced (unequal density) system, the excitons in the more dilute bilayer behave as polarons. We compute energies and effective masses of such exciton-polarons.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation

Model-based 3D pose and shape estimation methods reconstruct a full 3D mesh for the human body by estimating several parameters. However, learning the abstract parameters is a highly non-linear process and suffers from image-model misalignment, leading to mediocre model performance. In contrast, 3D keypoint estimation methods combine deep CNN network with the volumetric representation to achieve pixel-level localization accuracy but may predict unrealistic body structure. In this paper, we address the above issues by bridging the gap between body mesh estimation and 3D keypoint estimation. We propose a novel hybrid inverse kinematics solution (HybrIK). HybrIK directly transforms accurate 3D joints to relative body-part rotations for 3D body mesh reconstruction, via the twist-and-swing decomposition. The swing rotation is analytically solved with 3D joints, and the twist rotation is derived from the visual cues through the neural network. We show that HybrIK preserves both the accuracy of 3D pose and the realistic body structure of the parametric human model, leading to a pixel-aligned 3D body mesh and a more accurate 3D pose than the pure 3D keypoint estimation methods. Without bells and whistles, the proposed method surpasses the state-of-the-art methods by a large margin on various 3D human pose and shape benchmarks. As an illustrative example, HybrIK outperforms all the previous methods by 13.2 mm MPJPE and 21.9 mm PVE on 3DPW dataset. Our code is available at https://github.com/Jeff-sjtu/HybrIK.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Meeting-Merging-Mission: A Multi-robot Coordinate Framework for Large-Scale Communication-Limited Exploration

This letter presents a complete framework Meeting-Merging-Mission for multi-robot exploration under communication restriction. Considering communication is limited in both bandwidth and range in the real world, we propose a lightweight environment presentation method and an efficient cooperative exploration strategy. For lower bandwidth, each robot utilizes specific polytopes to maintains free space and super frontier information (SFI) as the source for exploration decision-making. To reduce repeated exploration, we develop a mission-based protocol that drives robots to share collected information in stable rendezvous. We also design a complete path planning scheme for both centralized and decentralized cases. To validate that our framework is practical and generic, we present an extensive benchmark and deploy our system into multi-UGV and multi-UAV platforms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Nonrelativistic axion electrodynamics in $p+is$ superconductors

In previous works, axion electrodynamics in three dimensional $p+is$ superconductors is discussed by borrowing the results from superconducting Dirac systems. However, in this work, based on a systematic path integral approach, we show that the axion electrodynamics in $p+is$ superconductors exhibits a nonrelativistic form, which is different from the superconducting Dirac and Weyl systems. More precisely, the induced electric field does not enter into the axion action, and gauge invariance is ensured by the combination of the electric potential and the Nambu-Goldstone phase mode. Furthermore, unlike the axion angle in the Dirac case which is equal to the difference between the superconducting phases on the two Fermi surfaces of different helicities, the axion angle in the present case contains an additional sinusoidal term. As applications of the derived nonrelativistic axion electrodynamics, physical effects related to vortex lines and Witten effect are discussed. Our work reveals the differences for axion electrodynamics between the relativistic and nonrelativistic systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

NPU-BOLT: A Dataset for Bolt Object Detection in Natural Scene Images

Bolt joints are very common and important in engineering structures. Due to extreme service environment and load factors, bolts often get loose or even disengaged. To real-time or timely detect the loosed or disengaged bolts is an urgent need in practical engineering, which is critical to keep structural safety and service life. In recent years, many bolt loosening detection methods using deep learning and machine learning techniques have been proposed and are attracting more and more attention. However, most of these studies use bolt images captured in laboratory for deep leaning model training. The images are obtained in a well-controlled light, distance, and view angle conditions. Also, the bolted structures are well designed experimental structures with brand new bolts and the bolts are exposed without any shelter nearby. It is noted that in practical engineering, the above well controlled lab conditions are not easy realized and the real bolt images often have blur edges, oblique perspective, partial occlusion and indistinguishable colors etc., which make the trained models obtained in laboratory conditions loss their accuracy or fails. Therefore, the aim of this study is to develop a dataset named NPU-BOLT for bolt object detection in natural scene images and open it to researchers for public use and further development. In the first version of the dataset, it contains 337 samples of bolt joints images mainly in the natural environment, with image data sizes ranging from 400*400 to 6000*4000, totaling approximately 1275 bolt targets. The bolt targets are annotated into four categories named blur bolt, bolt head, bolt nut and bolt side. The dataset is tested with advanced object detection models including yolov5, Faster-RCNN and CenterNet. The effectiveness of the dataset is validated.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Numerical investigation of the scale effects of rock bridges

The concept of joint persistence has been widely used to study the mechanics and failure processes of rock masses benefitting from the simplicity of statistical linear weighing of the discontinuity. Nevertheless, this term neglects the scale effects of rock bridges, meaning that the same joint persistence may refer to different numbers and spacings of rock bridges, leading to erroneous equivalent rock mass responses. To fill in this gap, an intact rock bridge was dispersed as multi rock bridges while maintaining a constant joint persistence, subjected to direct shear by conducting numerical simulations employing Universal Distinct Element Code (UDEC). In this way, scale effects of rock bridges were investigated from the perspective of load-displacement curves, stress and displacement fields, crack propagations and AE characterizations. Results revealed that the shear resistance and the area and value of stress-concentration decreased with increasing dispersion. Furthermore, uneven distribution of displacement fields in an arc manner moving and degrading away from the load was first observed, indicating the sequential failure of multi rock bridges. It was also found that the propagation of wing cracks was insensitive to scale, while the asperity of macro shear fracture mainly formed by secondary cracks decreased with increasing dispersion. In addition, increasing dispersion of rock bridges would overlap the failure precursors identified by intense AE activities. Based on the abovementioned results, we evaluated existing methods to characterize the joint persistence, and a threshold was observed to possibly define a rock bridge.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Origin of nonsymmorphic bosonization formulas in generalized antiferromagnetic Kitaev spin-$\frac{1}{2}$ chains from a renormalization-group perspective

Recently, in the Luttinger liquid phase of the one-dimensional generalized antiferromagnetic Kitaev spin-1/2 model, it has been found that the abelian bosonization formulas of the local spin operators only respect the exact discrete nonsymmorphic symmetry group of the model, not the emergent U(1) symmetry. In this work, we perform a renormalization group (RG) study to provide explanations for the origin of the U(1) breaking terms in the bosonization formulas. We find that the lack of U(1) symmetry originates from the wavefunction renormalization effects in the spin operators along the RG flow induced by the U(1) breaking interactions in the microscopic Hamiltonian. In addition, the RG analysis can give predictions to the signs and order of magnitudes of the coefficients in the bosonization formulas. Our work is helpful to understand the rich nonsymmorphic physics in one-dimensional Kitaev spin models.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

PartAfford: Part-level Affordance Discovery from 3D Objects

Understanding what objects could furnish for humans-namely, learning object affordance-is the crux to bridge perception and action. In the vision community, prior work primarily focuses on learning object affordance with dense (e.g., at a per-pixel level) supervision. In stark contrast, we humans learn the object affordance without dense labels. As such, the fundamental question to devise a computational model is: What is the natural way to learn the object affordance from visual appearance and geometry with humanlike sparse supervision? In this work, we present a new task of part-level affordance discovery (PartAfford): Given only the affordance labels per object, the machine is tasked to (i) decompose 3D shapes into parts and (ii) discover how each part of the object corresponds to a certain affordance category. We propose a novel learning framework for PartAfford, which discovers part-level representations by leveraging only the affordance set supervision and geometric primitive regularization, without dense supervision. The proposed approach consists of two main components: (i) an abstraction encoder with slot attention for unsupervised clustering and abstraction, and (ii) an affordance decoder with branches for part reconstruction, affordance prediction, and cuboidal primitive regularization. To learn and evaluate PartAfford, we construct a part-level, cross-category 3D object affordance dataset, annotated with 24 affordance categories shared among >25, 000 objects. We demonstrate that our method enables both the abstraction of 3D objects and part-level affordance discovery, with generalizability to difficult and cross-category examples. Further ablations reveal the contribution of each component.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Patch Slimming for Efficient Vision Transformers

This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series of computer vision tasks. However, similar to that of convolutional neural networks, the huge computational cost of vision transformers is still a severe issue. Considering that the attention mechanism aggregates different patches layer-by-layer, we present a novel patch slimming approach that discards useless patches in a top-down paradigm. We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers. For each layer, the impact of a patch on the final output feature is approximated and patches with less impact will be removed. Experimental results on benchmark datasets demonstrate that the proposed method can significantly reduce the computational costs of vision transformers without affecting their performances. For example, over 45% FLOPs of the ViT-Ti model can be reduced with only 0.2% top-1 accuracy drop on the ImageNet dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Real-Time Trajectory Planning for Aerial Perching

This paper presents a novel trajectory planning method for aerial perching. Compared with the existing work, the terminal states and the trajectory durations can be adjusted adaptively, instead of being determined in advance. Furthermore, our planner is able to minimize the tangential relative speed on the premise of safety and dynamic feasibility. This feature is especially notable on micro aerial robots with low maneuverability or scenarios where the space is not enough. Moreover, we design a flexible transformation strategy to eliminate terminal constraints along with reducing optimization variables. Besides, we take precise SE(3) motion planning into account to ensure that the drone would not touch the landing platform until the last moment. The proposed method is validated onboard by a palm-sized micro aerial robot with quite limited thrust and moment (thrust-to-weight ratio 1.7) perching on a mobile inclined surface. Sufficient experimental results show that our planner generates an optimal trajectory within 20ms, and replans with warm start in 2ms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Realization of the Trajectory Propagation in the MM-SQC Dynamics by Using Machine Learning

The supervised machine learning (ML) approach is applied to realize the trajectory-based nonadiabatic dynamics within the framework of the symmetrical quasi-classical dynamics method based on the Meyer-Miller mapping Hamiltonian (MM-SQC). After the construction of the long short-term memory recurrent neural network (LSTM-RNN) model, it is used to perform the entire trajectory evolutions from initial sampling conditions. The proposed idea is proven to be reliable and accurate in the simulations of the dynamics of several site-exciton electron-phonon coupling models, which cover two-site and three-site systems with biased and unbiased energy levels, as well as include a few or many phonon modes. The LSTM-RNN approach also shows the powerful ability to obtain the accurate and stable results for the long-time evolutions. It indicates that the LSTM-RNN model perfectly captures of dynamical correction information in the trajectory evolution in the MM-SQC dynamics. Our work provides the possibility to employ the ML methods in the simulation of the trajectory-based nonadiabatic dynamic of complex systems with a large number of degrees of freedoms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Region-Aware Face Swapping

This paper presents a novel Region-Aware Face Swapping (RAFSwap) network to achieve identity-consistent harmonious high-resolution face generation in a local-global manner: \textbf{1)} Local Facial Region-Aware (FRA) branch augments local identity-relevant features by introducing the Transformer to effectively model misaligned cross-scale semantic interaction. \textbf{2)} Global Source Feature-Adaptive (SFA) branch further complements global identity-relevant cues for generating identity-consistent swapped faces. Besides, we propose a \textit{Face Mask Predictor} (FMP) module incorporated with StyleGAN2 to predict identity-relevant soft facial masks in an unsupervised manner that is more practical for generating harmonious high-resolution faces. Abundant experiments qualitatively and quantitatively demonstrate the superiority of our method for generating more identity-consistent high-resolution swapped faces over SOTA methods, \eg, obtaining 96.70 ID retrieval that outperforms SOTA MegaFS by 5.87$\uparrow$.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline is redundant and inefficient for the independent processes, and some inner features could have been shared. Therefore, we present an efficient paradigm to perform {S}imultaneously Image {C}olorization and {S}uper-resolution (SCS) and propose an end-to-end SCSNet to achieve this goal. The proposed method consists of two parts: colorization branch for learning color information that employs the proposed plug-and-play \emph{Pyramid Valve Cross Attention} (PVCAttn) module to aggregate feature maps between source and reference images; and super-resolution branch for integrating color and texture information to predict target images, which uses the designed \emph{Continuous Pixel Mapping} (CPM) module to predict high-resolution images at continuous magnification. Furthermore, our SCSNet supports both automatic and referential modes that is more flexible for practical application. Abundant experiments demonstrate the superiority of our method for generating authentic images over state-of-the-art methods, e.g., averagely decreasing FID by 1.8$\downarrow$ and 5.1 $\downarrow$ compared with current best scores for automatic and referential modes, respectively, while owning fewer parameters (more than $\times$2$\downarrow$) and faster running speed (more than $\times$3$\uparrow$).

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Solving systems of linear equations through zero forcing set and application to lights out

Let $\mathbb{F}$ be any field, we consider solving $Ax=b$ repeatedly for a matrix $A\in\mathbb{F}^{n\times n}$ of $m$ non-zero elements, and multiple different $b\in\mathbb{F}^{n}$. If we are given a zero forcing set of $A$ of size $k$, we can then build a data structure in $O(mk)$ time, such that each instance of $Ax=b$ can be solved in $O(k^2+m)$ time. As an application, we show how the lights out game in an $n\times n$ grid is solved in $O(n^3)$ time, and then improve the running time to $O(n^ω\log n)$ by exploiting the repeated structure in grids.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Star-Convex Constrained Optimization for Visibility Planning with Application to Aerial Inspection

The visible capability is critical in many robot applications, such as inspection and surveillance, etc. Without the assurance of the visibility to targets, some tasks end up not being complete or even failing. In this paper, we propose a visibility guaranteed planner by star-convex constrained optimization. The visible space is modeled as star convex polytope (SCP) by nature and is generated by finding the visible points directly on point cloud. By exploiting the properties of the SCP, the visibility constraint is formulated for trajectory optimization. The trajectory is confined in the safe and visible flight corridor which consists of convex polytopes and SCPs. We further make a relaxation to the visibility constraints and transform the constrained trajectory optimization problem into an unconstrained one that can be reliably and efficiently solved. To validate the capability of the proposed planner, we present the practical application in site inspection. The experimental results show that the method is efficient, scalable, and visibility guaranteed, presenting the prospect of application to various other applications in the future.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The Visual-Inertial-Dynamical Multirotor Dataset

Recently, the community has witnessed numerous datasets built for developing and testing state estimators. However, for some applications such as aerial transportation or search-and-rescue, the contact force or other disturbance must be perceived for robust planning and control, which is beyond the capacity of these datasets. This paper introduces a Visual-Inertial-Dynamical (VID) dataset, not only focusing on traditional six degrees of freedom (6-DOF) pose estimation but also providing dynamical characteristics of the flight platform for external force perception or dynamics-aided estimation. The VID dataset contains hardware synchronized imagery and inertial measurements, with accurate ground truth trajectories for evaluating common visual-inertial estimators. Moreover, the proposed dataset highlights rotor speed and motor current measurements, control inputs, and ground truth 6-axis force data to evaluate external force estimation. To the best of our knowledge, the proposed VID dataset is the first public dataset containing visual-inertial and complete dynamical information in the real world for pose and external force evaluation. The dataset: https://github.com/ZJU-FAST-Lab/VID-Dataset and related files: https://github.com/ZJU-FAST-Lab/VID-Flight-Platform are open-sourced.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

CMPCC: Corridor-based Model Predictive Contouring Control for Aggressive Drone Flight

In this paper, we propose an efficient, receding horizon, local adaptive low-level planner as the middle layer between our original planner and controller. Our method is named as corridor-based model predictive contouring control (CMPCC) since it builds upon on MPCC and utilizes the flight corridor as hard safety constraints. It optimizes the flight aggressiveness and tracking accuracy simultaneously, thus improving our system's robustness by overcoming unmeasured disturbances. Our method features its online flight speed optimization, strict safety and feasibility, and real-time performance, and will be released as a low-level plugin for a large variety of quadrotor systems.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Integrating Fast Regional Optimization into Sampling-based Kinodynamic Planning for Multirotor Flight

For real-time multirotor kinodynamic motion planning, the efficiency of sampling-based methods is usually hindered by difficult-to-sample homotopy classes like narrow passages. In this paper, we address this issue by a hybrid scheme. We firstly propose a fast regional optimizer exploiting the information of local environments and then integrate it into a global sampling process to ensure faster convergence. The incorporation of local optimization on different sampling-based methods shows significantly improved success rates and less planning time in various types of challenging environments. We also present a refinement module that fully investigates the resulting trajectory of the global sampling and greatly improves its smoothness with negligible computation effort. Benchmark results illustrate that compared to the state-of-the-art ones, our proposed method can better exploit a previous trajectory. The planning methods are applied to generate trajectories for a simulated quadrotor system, and its capability is validated in real-time applications.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

SCOP: Scientific Control for Reliable Neural Network Pruning

This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Existing pruning methods have developed various hypotheses to approximate the importance of filters to the network and then execute filter pruning accordingly. To increase the reliability of the results, we prefer to have a more rigorous research design by including a scientific control group as an essential part to minimize the effect of all factors except the association between the filter and expected network output. Acting as a control group, knockoff feature is generated to mimic the feature map produced by the network filter, but they are conditionally independent of the example label given the real feature map. We theoretically suggest that the knockoff condition can be approximately preserved given the information propagation of network layers. Besides the real feature map on an intermediate layer, the corresponding knockoff feature is brought in as another auxiliary input signal for the subsequent layers. Redundant filters can be discovered in the adversarial process of different features. Through experiments, we demonstrate the superiority of the proposed algorithm over state-of-the-art methods. For example, our method can reduce 57.8% parameters and 60.2% FLOPs of ResNet-101 with only 0.01% top-1 accuracy loss on ImageNet. The code is available at https://github.com/huawei-noah/Pruning/tree/master/SCOP_NeurIPS2020.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

The Paradox of Information Access: On Modeling Social-Media-Induced Polarization

The paper develops a stochastic model of drift in human beliefs that shows that today's sheer volume of accessible information, combined with consumers' confirmation bias and natural preference to more outlying content, necessarily lead to increased polarization. The model explains the paradox of growing ideological fragmentation in the age of increased sharing. As social media, search engines, and other real-time information sharing outlets purport to facilitate access to information, a need for content filtering arises due to the ensuing information overload. In general, consumers select information that matches their individual views and values. The bias inherent in such selection is echoed by today's information curation services that maximize user engagement by filtering new content in accordance with observed consumer preferences. Consequently, individuals get exposed to increasingly narrower bands of the ideology spectrum, thus fragmenting society into increasingly ideologically isolated enclaves. We call this dynamic the paradox of information access. The model also suggests the disproportionate damage attainable with a small infusion of well-positioned misinformation. The paper describes the modeling methodology, and evaluates modeling results for different population sizes and parameter settings.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Alternating Minimization Based Trajectory Generation for Quadrotor Aggressive Flight

With much research has been conducted into trajectory planning for quadrotors, planning with spatial and temporal optimal trajectories in real-time is still challenging. In this paper, we propose a framework for generating large-scale piecewise polynomial trajectories for aggressive autonomous flights, with highlights on its superior computational efficiency and simultaneous spatial-temporal optimality. Exploiting the implicitly decoupled structure of the planning problem, we conduct alternating minimization between boundary conditions and time durations of trajectory pieces. In each minimization phase, we leverage the algebraic convenience of the sub-problem to escape poor local minima and achieve the lowest time consumption. Theoretical analysis for the global/local convergence rate of our proposed method is provided. Moreover, based on polynomial theory, an extremely fast feasibility check method is designed for various kinds of constraints. By incorporating the method into our alternating structure, a constrained minimization algorithm is constructed to optimize trajectories on the premise of feasibility. Benchmark evaluation shows that our algorithm outperforms state-of-the-art methods regarding efficiency, optimality, and scalability. Aggressive flight experiments in a limited space with dense obstacles are presented to demonstrate the performance of the proposed algorithm. We release our implementation as an open-source ros-package.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

AoI and Energy Consumption Oriented Dynamic Status Updating in Caching Enabled IoT Networks

Caching has been regarded as a promising technique to alleviate energy consumption of sensors in Internet of Things (IoT) networks by responding to users' requests with the data packets stored in the edge caching node (ECN). For real-time applications in caching enabled IoT networks, it is essential to develop dynamic status update strategies to strike a balance between the information freshness experienced by users and energy consumed by the sensor, which, however, is not well addressed. In this paper, we first depict the evolution of information freshness, in terms of age of information (AoI), at each user. Then, we formulate a dynamic status update optimization problem to minimize the expectation of a long term accumulative cost, which jointly considers the users' AoI and sensor's energy consumption. To solve this problem, a Markov Decision Process (MDP) is formulated to cast the status updating procedure, and a model-free reinforcement learning algorithm is proposed, with which the challenge brought by the unknown of the formulated MDP's dynamics can be addressed. Finally, simulations are conducted to validate the convergence of our proposed algorithm and its effectiveness compared with the zero-wait baseline policy.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Attractive and repulsive dipolar interaction in bilayers of indirect excitons

We explore attractive dipolar interaction in indirect excitons (IXs). For one layer of IXs in a single pair of coupled quantum wells (CQW), the out-of-plane IX electric dipoles lead to repulsive dipolar interaction between IXs. The attractive dipolar interaction between IXs is realized in a 2-CQW heterostructure with two IX layers in two separated CQW pairs. We found both in experimental measurements and theoretical simulations that increasing density of IXs in one layer causes a monotonic energy reduction for IXs in the other layer. We also found an in-plane shift of a cloud of IXs in one layer towards a cloud of IXs in the other layer. This behaviour is qualitatively consistent with attractive dipolar interaction. The measured IX energy reduction and IX cloud shift are higher than the values given by the correlated liquid theory.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Average Age of Changed Information in the Internet of Things

The freshness of status updates is imperative in mission-critical Internet of things (IoT) applications. Recently, Age of Information (AoI) has been proposed to measure the freshness of updates at the receiver. However, AoI only characterizes the freshness over time, but ignores the freshness in the content. In this paper, we introduce a new performance metric, Age of Changed Information (AoCI), which captures both the passage of time and the change of information content. Also, we examine the AoCI in a time-slotted status update system, where a sensor samples the physical process and transmits the update packets with a cost. We formulate a Markov Decision Process (MDP) to find the optimal updating policy that minimizes the weighted sum of the AoCI and the update cost. Particularly, in a special case that the physical process is modeled by a two-state discrete time Markov chain with equal transition probability, we show that the optimal policy is of threshold type with respect to the AoCI and derive the closed-form of the threshold. Finally, simulations are conducted to exhibit the performance of the threshold policy and its superiority over the zero-wait baseline policy.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks

Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. On one hand, massive trainable parameters significantly enhance the performance of these deep networks. On the other hand, they bring the problem of over-fitting. To this end, dropout based methods disable some elements in the output feature maps during the training phase for reducing the co-adaptation of neurons. Although the generalization ability of the resulting models can be enhanced by these approaches, the conventional binary dropout is not the optimal solution. Therefore, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks and propose a feature distortion method (Disout) for addressing the aforementioned problem. In the training period, randomly selected elements in the feature maps will be replaced with specific values by exploiting the generalization error bound. The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated on several benchmark image datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

CARS: Continuous Evolution for Efficient Neural Architecture Search

Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for searching neural networks. Architectures in the population that share parameters within one SuperNet in the latest generation will be tuned over the training dataset with a few epochs. The searching in the next evolution generation will directly inherit both the SuperNet and the population, which accelerates the optimal network generation. The non-dominated sorting strategy is further applied to preserve only results on the Pareto front for accurately updating the SuperNet. Several neural networks with different model sizes and performances will be produced after the continuous search with only 0.4 GPU days. As a result, our framework provides a series of networks with the number of parameters ranging from 3.7M to 5.1M under mobile settings. These networks surpass those produced by the state-of-the-art methods on the benchmark ImageNet dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep Learning Based Antenna Selection for Channel Extrapolation in FDD Massive MIMO

In massive multiple-input multiple-output (MIMO) systems, the large number of antennas would bring a great challenge for the acquisition of the accurate channel state information, especially in the frequency division duplex mode. To overcome the bottleneck of the limited number of radio links in hybrid beamforming, we utilize the neural networks (NNs) to capture the inherent connection between the uplink and downlink channel data sets and extrapolate the downlink channels from a subset of the uplink channel state information. We study the antenna subset selection problem in order to achieve the best channel extrapolation and decrease the data size of NNs. The probabilistic sampling theory is utilized to approximate the discrete antenna selection as a continuous and differentiable function, which makes the back propagation of the deep learning feasible. Then, we design the proper off-line training strategy to optimize both the antenna selection pattern and the extrapolation NNs. Finally, numerical results are presented to verify the effectiveness of our proposed massive MIMO channel extrapolation algorithm.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Detailed Proofs of Alternating Minimization Based Trajectory Generation for Quadrotor Aggressive Flight

This technical report provides detailed theoretical analysis of the algorithm used in \textit{Alternating Minimization Based Trajectory Generation for Quadrotor Aggressive Flight}. An assumption is provided to ensure that settings for the objective function are meaningful. What's more, we explore the structure of the optimization problem and analyze the global/local convergence rate of the employed algorithm.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Discernible Image Compression

Image compression, as one of the fundamental low-level image processing tasks, is very essential for computer vision. Tremendous computing and storage resources can be preserved with a trivial amount of visual information. Conventional image compression methods tend to obtain compressed images by minimizing their appearance discrepancy with the corresponding original images, but pay little attention to their efficacy in downstream perception tasks, e.g., image recognition and object detection. Thus, some of compressed images could be recognized with bias. In contrast, this paper aims to produce compressed images by pursuing both appearance and perceptual consistency. Based on the encoder-decoder framework, we propose using a pre-trained CNN to extract features of the original and compressed images, and making them similar. Thus the compressed images are discernible to subsequent tasks, and we name our method as Discernible Image Compression (DIC). In addition, the maximum mean discrepancy (MMD) is employed to minimize the difference between feature distributions. The resulting compression network can generate images with high image quality and preserve the consistent perception in the feature domain, so that these images can be well recognized by pre-trained machine learning models. Experiments on benchmarks demonstrate that images compressed by using the proposed method can also be well recognized by subsequent visual recognition and detection models. For instance, the mAP value of compressed images by DIC is about 0.6% higher than that of using compressed images by conventional methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Distilling portable Generative Adversarial Networks for Image Translation

Despite Generative Adversarial Networks (GANs) have been widely used in various image-to-image translation tasks, they can be hardly applied on mobile devices due to their heavy computation and storage cost. Traditional network compression methods focus on visually recognition tasks, but never deal with generation tasks. Inspired by knowledge distillation, a student generator of fewer parameters is trained by inheriting the low-level and high-level information from the original heavy teacher generator. To promote the capability of student generator, we include a student discriminator to measure the distances between real images, and images generated by student and teacher generators. An adversarial learning process is therefore established to optimize student generator and student discriminator. Qualitative and quantitative analysis by conducting experiments on benchmark datasets demonstrate that the proposed method can learn portable generative models with strong performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Hierarchical and Efficient Learning for Person Re-Identification

Recent works in the person re-identification task mainly focus on the model accuracy while ignore factors related to the efficiency, e.g. model size and latency, which are critical for practical application. In this paper, we propose a novel Hierarchical and Efficient Network (HENet) that learns hierarchical global, partial, and recovery features ensemble under the supervision of multiple loss combinations. To further improve the robustness against the irregular occlusion, we propose a new dataset augmentation approach, dubbed Random Polygon Erasing (RPE), to random erase irregular area of the input image for imitating the body part missing. We also propose an Efficiency Score (ES) metric to evaluate the model efficiency. Extensive experiments on Market1501, DukeMTMC-ReID, and CUHK03 datasets shows the efficiency and superiority of our approach compared with epoch-making methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multicritera Cuts and Size-Constrained $k$-cuts in Hypergraphs

We address counting and optimization variants of multicriteria global min-cut and size-constrained min-$k$-cut in hypergraphs. 1. For an $r$-rank $n$-vertex hypergraph endowed with $t$ hyperedge-cost functions, we show that the number of multiobjective min-cuts is $O(r2^{tr}n^{3t-1})$. In particular, this shows that the number of parametric min-cuts in constant rank hypergraphs for a constant number of criteria is strongly polynomial, thus resolving an open question by Aissi, Mahjoub, McCormick, and Queyranne (Math Programming, 2015). In addition, we give randomized algorithms to enumerate all multiobjective min-cuts and all pareto-optimal cuts in strongly polynomial-time. 2. We also address node-budgeted multiobjective min-cuts: For an $n$-vertex hypergraph endowed with $t$ vertex-weight functions, we show that the number of node-budgeted multiobjective min-cuts is $O(r2^{r}n^{t+2})$, where $r$ is the rank of the hypergraph, and the number of node-budgeted $b$-multiobjective min-cuts for a fixed budget-vector $b$ is $O(n^2)$. 3. We show that min-$k$-cut in hypergraphs subject to constant lower bounds on part sizes is solvable in polynomial-time for constant $k$, thus resolving an open problem posed by Queyranne. Our technique also shows that the number of optimal solutions is polynomial. All of our results build on the random contraction approach of Karger (SODA, 1993). Our techniques illustrate the versatility of the random contraction approach to address counting and algorithmic problems concerning multiobjective min-cuts and size-constrained $k$-cuts in hypergraphs.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On Positive-Unlabeled Classification in GAN

This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs. Traditionally, real data are taken as positive while generated data are negative. This positive-negative classification criterion was kept fixed all through the learning process of the discriminator without considering the gradually improved quality of generated data, even if they could be more realistic than real data at times. In contrast, it is more reasonable to treat the generated data as unlabeled, which could be positive or negative according to their quality. The discriminator is thus a classifier for this positive and unlabeled classification problem, and we derive a new Positive-Unlabeled GAN (PUGAN). We theoretically discuss the global optimality the proposed model will achieve and the equivalent optimization goal. Empirically, we find that PUGAN can achieve comparable or even better performance than those sophisticated discriminator stabilization methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Searching for Low-Bit Weights in Quantized Neural Networks

Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators. However, the quantization functions used in most conventional quantization methods are non-differentiable, which increases the optimization difficulty of quantized networks. Compared with full-precision parameters (i.e., 32-bit floating numbers), low-bit values are selected from a much smaller set. For example, there are only 16 possibilities in 4-bit space. Thus, we present to regard the discrete weights in an arbitrary quantized neural network as searchable variables, and utilize a differential method to search them accurately. In particular, each weight is represented as a probability distribution over the discrete value set. The probabilities are optimized during training and the values with the highest probability are selected to establish the desired quantized network. Experimental results on benchmarks demonstrate that the proposed method is able to produce quantized neural networks with higher performance over the state-of-the-art methods on both image classification and super-resolution tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Single branch of chiral Majorana modes from doubly degenerate Fermi surfaces

Majorana fermions are often proposed to be realized by first singling out one Fermi surface without spin degeneracy via spin-orbit coupling, and then imposing boundaries or defects. In this work, we take a different route starting with two degenerate Fermi surfaces without spin-orbit coupling, and show that by the method of "kink on boundary", the dispersive chiral Majorana fermions can be realized in superconducting systems with $p\pm is$ pairings. The surfaces of these systems develop spontaneous magnetizations whose directions are determined by the boundary orientations and the phase difference between the $p$ and $s$-component gap functions. Along the magnetic domain walls on the surface, there exist chiral Majorana fermions propagating unidirectionally, which can be conveniently dragged and controlled by external magnetic fields. Furthermore, the surface magnetization is shown to be a magnetoelectric effect based on a Ginzburg-Landau free energy analysis. We also discuss how to use the proximity effects to realize chiral Majorana fermions by performing the "kink on boundary" method.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The Paradox of Information Access: Growing Isolation in the Age of Sharing

Modern online media, such as Twitter, Instagram, and YouTube, enable anyone to become an information producer and to offer online content for potentially global consumption. By increasing the amount of globally accessible real-time information, today's ubiquitous producers contribute to a world, where an individual consumes vanishingly smaller fractions of all produced content. In general, consumers preferentially select information that closely matches their individual views and values. The bias inherent in such selection is further magnified by today's information curation services that maximize user engagement (and thus service revenue) by filtering new content in accordance with observed consumer preferences. Consequently, individuals get exposed to increasingly narrower bands of the ideology spectrum. Societies get fragmented into increasingly ideologically isolated enclaves. These enclaves (or echo-chambers) then become vulnerable to misinformation spread, which in turn further magnifies polarization and bias. We call this dynamic the paradox of information access; a growing ideological fragmentation in the age of sharing. This article describes the technical, economic, and socio-cognitive contributors to this paradox, and explores research directions towards its mitigation.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Data-Free Learning of Student Networks

Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep neural network compression and speed-up methods are very effective for training compact deep models, when we can directly access the training dataset. However, training data for the given deep network are often unavailable due to some practice problems (e.g. privacy, legal issue, and transmission), and the architecture of the given network are also unknown except some interfaces. To this end, we propose a novel framework for training efficient deep neural networks by exploiting generative adversarial networks (GANs). To be specific, the pre-trained teacher networks are regarded as a fixed discriminator and the generator is utilized for derivating training samples which can obtain the maximum response on the discriminator. Then, an efficient network with smaller model size and computational complexity is trained using the generated data and the teacher network, simultaneously. Efficient student networks learned using the proposed Data-Free Learning (DAFL) method achieve 92.22% and 74.47% accuracies using ResNet-18 without any training data on the CIFAR-10 and CIFAR-100 datasets, respectively. Meanwhile, our student network obtains an 80.56% accuracy on the CelebA benchmark.

0 citations0 reviewsNo code linkedOpen access