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

Wen Yang

Wen Yang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer Visionmath.APMachine Learningeess.IVRoboticscond-mat.mes-hallcond-mat.mtrl-sciquant-phComputation and LanguageMultimediaphysics.atom-phphysics.optics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
32works
0followers
12topics
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

32 published item(s)

preprint2026arXiv

AIMS: An Adaptive Integration of Multi-Sensor Measurements for Quadrupedal Robot Localization

This paper addresses the problem of accurate localization for quadrupedal robots operating in narrow tunnel-like environments. Due to the long and homogeneous characteristics of such scenarios, LiDAR measurements often provide weak geometric constraints, making traditional sensor fusion methods susceptible to accumulated motion estimation errors. To address these challenges, we propose AIMS, an adaptive LiDAR-IMU-leg odometry fusion method for robust quadrupedal robot localization in degenerate environments. The proposed method is formulated within an error-state Kalman filtering framework, where LiDAR and leg odometry measurements are integrated with IMU-based state prediction, and measurement noise covariance matrices are adaptively adjusted based on online degeneracy-aware reliability assessment. Experimental results obtained in narrow corridor environments demonstrate that the proposed method improves localization accuracy and robustness compared with state-of-the-art approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

MOC-3D: Manifold-Order Consistency for Text-to-3D Generation

With the burgeoning development of fields such as the Metaverse, Virtual Reality (VR), and Digital Twins, text-to-3D generation has emerged as a research hotspot in both academia and industry. Currently, optimization methods based on Score Distillation Sampling (SDS) utilizing 2D diffusion priors have become the mainstream technological paradigm in this field. However, due to the view bias of 2D priors and the mode-seeking ambiguity combined with gradient noise induced by high Classifier-Free Guidance (CFG), these methods still suffer from macro-topological inconsistency (e.g., the Janus problem) and micro-geometric discontinuity. To address these challenges, we propose MOC-3D, a text-to-3D generation method based on geometric manifold and semantic view-order consistency. Built upon the ScaleDreamer framework, our method incorporates a Semantic View-Order Constraint Module and a Manifold-based Feature Continuity Module. The former aims to rectify macro-topological inconsistency, while the latter focuses on eliminating micro-geometric discontinuity. Specifically, the Semantic View-Order Constraint Module leverages the prior knowledge of CLIP to impose a Monotonicity Rank Constraint on semantic score representations across different views, thereby providing effective guidance for the global topological structure of 3D objects. Meanwhile, the Manifold-based Feature Continuity Module employs the Riemannian Metric on the Symmetric Positive Definite (SPD) manifold. By measuring the distance of feature statistical distributions in the Riemannian space, it promotes the smooth evolution and continuity of micro-textures across multi-views in a statistical sense. Under the macro-micro synergistic optimization of these two modules, our model can simultaneously improve macro-structural consistency and micro-detail continuity.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow down the training and inference of LLMs. The fine-grained knowledge transfer between LLMs, like token-level distillation, is also impeded by the mismatch in vocabulary. To bridge this gap, we introduce a method named TokAlign++ to improve vocabulary adaptation performance by learning better token alignment lexicon. The source and target vocabularies are taken as two different languages, and the bilingual token alignment lexicon is learned from monolingual token representations. Model parameters are rearranged following this bilingual lexicon for new vocabulary, and progressively fine-tuned for adaptation. Experimental results on 15 languages show that our method boosts the multilingual text compression rates and preserves most of the multilingual ability of vanilla models. It costs as few as 1k steps to restore the performance of the vanilla model. After unifying vocabularies between vanilla models, token-level distillation remarkably improves the base model with only 235M tokens.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Normalized Gaussian Wasserstein Distance for Tiny Object Detection

Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory results on tiny objects due to the lack of appearance information. Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors. To alleviate this, we propose a new evaluation metric using Wasserstein distance for tiny object detection. Specifically, we first model the bounding boxes as 2D Gaussian distributions and then propose a new metric dubbed Normalized Wasserstein Distance (NWD) to compute the similarity between them by their corresponding Gaussian distributions. The proposed NWD metric can be easily embedded into the assignment, non-maximum suppression, and loss function of any anchor-based detector to replace the commonly used IoU metric. We evaluate our metric on a new dataset for tiny object detection (AI-TOD) in which the average object size is much smaller than existing object detection datasets. Extensive experiments show that, when equipped with NWD metric, our approach yields performance that is 6.7 AP points higher than a standard fine-tuning baseline, and 6.0 AP points higher than state-of-the-art competitors. Codes are available at: https://github.com/jwwangchn/NWD.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A novel method for data augmentation: Nine Dot Moving Least Square (ND-MLS)

Data augmentation greatly increases the amount of data obtained based on labeled data to save on expenses and labor for data collection and labeling. We present a new approach for data augmentation called nine-dot MLS (ND-MLS). This approach is proposed based on the idea of image defor-mation. Images are deformed based on control points, which are calculated by ND-MLS. The method can generate over 2000 images for one exist-ing dataset in a short time. To verify this data augmentation method, extensive tests were performed covering 3 main tasks of computer vision, namely, classification, detection and segmentation. The results show that 1) in classification, 10 images per category were used for training, and VGGNet can obtain 92% top-1 acc on the MNIST dataset of handwritten digits by ND-MLS. In the Omniglot dataset, the few-shot accuracy usu-ally decreases with the increase in character categories. However, the ND-MLS method has stable performance and obtains 96.5 top-1 acc in Res-Net on 100 different handwritten character classification tasks; 2) in segmentation, under the premise of only ten original images, DeepLab obtains 93.5%, 85%, and 73.3% m_IOU(10) on the bottle, horse, and grass test datasets, respectively, while the cat test dataset obtains 86.7% m_IOU(10) with the SegNet model; 3) with only 10 original images from each category in object detection, YOLO v4 obtains 100% and 97.2% bottle and horse detection, respectively, while the cat dataset obtains 93.6% with YOLO v3. In summary, ND-MLS can perform well on classification, object detec-tion, and semantic segmentation tasks by using only a few data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Survey of Uncertainty in Deep Neural Networks

Due to their increasing spread, confidence in neural network predictions became more and more important. However, basic neural networks do not deliver certainty estimates or suffer from over or under confidence. Many researchers have been working on understanding and quantifying uncertainty in a neural network's prediction. As a result, different types and sources of uncertainty have been identified and a variety of approaches to measure and quantify uncertainty in neural networks have been proposed. This work gives a comprehensive overview of uncertainty estimation in neural networks, reviews recent advances in the field, highlights current challenges, and identifies potential research opportunities. It is intended to give anyone interested in uncertainty estimation in neural networks a broad overview and introduction, without presupposing prior knowledge in this field. A comprehensive introduction to the most crucial sources of uncertainty is given and their separation into reducible model uncertainty and not reducible data uncertainty is presented. The modeling of these uncertainties based on deterministic neural networks, Bayesian neural networks, ensemble of neural networks, and test-time data augmentation approaches is introduced and different branches of these fields as well as the latest developments are discussed. For a practical application, we discuss different measures of uncertainty, approaches for the calibration of neural networks and give an overview of existing baselines and implementations. Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications. Additionally, the practical limitations of current methods for mission- and safety-critical real world applications are discussed and an outlook on the next steps towards a broader usage of such methods is given.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark

Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection over Union (IoU) metric and its extensions are very sensitive to the location deviation of the tiny objects, which drastically deteriorates the quality of label assignment when used in anchor-based detectors. To tackle this problem, we propose a new evaluation metric dubbed Normalized Wasserstein Distance (NWD) and a new RanKing-based Assigning (RKA) strategy for tiny object detection. The proposed NWD-RKA strategy can be easily embedded into all kinds of anchor-based detectors to replace the standard IoU threshold-based one, significantly improving label assignment and providing sufficient supervision information for network training. Tested on four datasets, NWD-RKA can consistently improve tiny object detection performance by a large margin. Besides, observing prominent noisy labels in the Tiny Object Detection in Aerial Images (AI-TOD) dataset, we are motivated to meticulously relabel it and release AI-TOD-v2 and its corresponding benchmark. In AI-TOD-v2, the missing annotation and location error problems are considerably mitigated, facilitating more reliable training and validation processes. Embedding NWD-RKA into DetectoRS, the detection performance achieves 4.3 AP points improvement over state-of-the-art competitors on AI-TOD-v2. Datasets, codes, and more visualizations are available at: https://chasel-tsui.github.io/AI-TOD-v2/

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Electron-mediated projective quantum nondemolition measurement on a nuclear spin

Projective quantum nondemolition (QND) measurement is important for quantum technologies. Here we propose a method for constructing projective QND measurement on a nuclear spin via the measurement of an axillary electron spin in generic electron-nuclear spin systems coupled through weak hyperfine interaction. The key idea is to apply suitable quantum control on the electron to construct a weak QND measurement on the nuclear spin and then cascade a sequence of such measurements into a projective one. We identify a set of tunable parameters to select the QND observables and control the strength of the weak QND measurement. We also find that the QND measurement can be stabilized against realistic experimental control errors. As a demonstration of our method, we design projective QND measurement on a $^{13}$C nuclear spin weakly coupled to a nitrogen-vacancy center electron spin in diamond.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

First-principles study on the solute-induced low diffusion and self-trapping of helium in fcc iron

The addition of alloying elements plays an essential role in helium (He) behaviours produced by transmutation in metal alloys. Effects of solutes (Ni, Cr, Ti, P, Si, C) on the behaviours of He and He-He pair in face-centred cube (fcc) iron have been investigated using first-principles calculations based on density functional theory (DFT). For the interactions of solutes and He, we found that Ti, P, Si, and C attracts He is more potent than Ni and Cr in fcc iron. We have determined the most stable configuration for the He-He pair, which is the Hesub-Hetetra pair with a binding energy of 1.60 eV. In considering the effect of solutes on the stability of the He-He pair, we have proposed a unique definition of binding energy. By applying the definition, we suggest that Ti and P could weaken He self-trapping, and Cr and C are beneficial for He self-trapping, while Ni is similar to the matrix Fe itself. For the diffusion of He, which is the necessary process of forming the He bubble, we determined that the most stable interstitial He is in a tetrahedral site and could migrate with the energy barrier of 0.16 eV in pure fcc iron. We further found that Ti and Si can increase the barrier to 0.18 and 0.20 eV; on the contrary, Cr and P decrease the barrier to 0.10 and 0.06 eV, respectively. Summarizing the calculations, we conclude that Ti decreases while Cr increases the diffusion and self-trapping of He in fcc iron.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

GLF-CR: SAR-Enhanced Cloud Removal with Global-Local Fusion

The challenge of the cloud removal task can be alleviated with the aid of Synthetic Aperture Radar (SAR) images that can penetrate cloud cover. However, the large domain gap between optical and SAR images as well as the severe speckle noise of SAR images may cause significant interference in SAR-based cloud removal, resulting in performance degeneration. In this paper, we propose a novel global-local fusion based cloud removal (GLF-CR) algorithm to leverage the complementary information embedded in SAR images. Exploiting the power of SAR information to promote cloud removal entails two aspects. The first, global fusion, guides the relationship among all local optical windows to maintain the structure of the recovered region consistent with the remaining cloud-free regions. The second, local fusion, transfers complementary information embedded in the SAR image that corresponds to cloudy areas to generate reliable texture details of the missing regions, and uses dynamic filtering to alleviate the performance degradation caused by speckle noise. Extensive evaluation demonstrates that the proposed algorithm can yield high quality cloud-free images and outperform state-of-the-art cloud removal algorithms with a gain about 1.7dB in terms of PSNR on SEN12MS-CR dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Graph-Based Similarity of Neural Network Representations

Understanding the black-box representations in Deep Neural Networks (DNN) is an essential problem in deep learning. In this work, we propose Graph-Based Similarity (GBS) to measure the similarity of layer features. Contrary to previous works that compute the similarity directly on the feature maps, GBS measures the correlation based on the graph constructed with hidden layer outputs. By treating each input sample as a node and the corresponding layer output similarity as edges, we construct the graph of DNN representations for each layer. The similarity between graphs of layers identifies the correspondences between representations of models trained in different datasets and initializations. We demonstrate and prove the invariance property of GBS, including invariance to orthogonal transformation and invariance to isotropic scaling, and compare GBS with CKA. GBS shows state-of-the-art performance in reflecting the similarity and provides insights on explaining the adversarial sample behavior on the hidden layer space.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning to Extract Building Footprints from Off-Nadir Aerial Images

Extracting building footprints from aerial images is essential for precise urban mapping with photogrammetric computer vision technologies. Existing approaches mainly assume that the roof and footprint of a building are well overlapped, which may not hold in off-nadir aerial images as there is often a big offset between them. In this paper, we propose an offset vector learning scheme, which turns the building footprint extraction problem in off-nadir images into an instance-level joint prediction problem of the building roof and its corresponding "roof to footprint" offset vector. Thus the footprint can be estimated by translating the predicted roof mask according to the predicted offset vector. We further propose a simple but effective feature-level offset augmentation module, which can significantly refine the offset vector prediction by introducing little extra cost. Moreover, a new dataset, Buildings in Off-Nadir Aerial Images (BONAI), is created and released in this paper. It contains 268,958 building instances across 3,300 aerial images with fully annotated instance-level roof, footprint, and corresponding offset vector for each building. Experiments on the BONAI dataset demonstrate that our method achieves the state-of-the-art, outperforming other competitors by 3.37 to 7.39 points in F1-score. The codes, datasets, and trained models are available at https://github.com/jwwangchn/BONAI.git.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Lidar with Velocity: Correcting Moving Objects Point Cloud Distortion from Oscillating Scanning Lidars by Fusion with Camera

Lidar point cloud distortion from moving object is an important problem in autonomous driving, and recently becomes even more demanding with the emerging of newer lidars, which feature back-and-forth scanning patterns. Accurately estimating moving object velocity would not only provide a tracking capability but also correct the point cloud distortion with more accurate description of the moving object. Since lidar measures the time-of-flight distance but with a sparse angular resolution, the measurement is precise in the radial measurement but lacks angularly. Camera on the other hand provides a dense angular resolution. In this paper, Gaussian-based lidar and camera fusion is proposed to estimate the full velocity and correct the lidar distortion. A probabilistic Kalman-filter framework is provided to track the moving objects, estimate their velocities and simultaneously correct the point clouds distortions. The framework is evaluated on real road data and the fusion method outperforms the traditional ICP-based and point-cloud only method. The complete working framework is open-sourced (https://github.com/ISEE-Technology/lidar-with-velocity) to accelerate the adoption of the emerging lidars.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The Blow-up Analysis on $\mathbf{B}_2^{(1)}$ Affine Toda system: Local mass and Affine Weyl group

It has been established that the local mass of blow-up solutions to Toda systems associated with the simple Lie algebras $\mathbf{A}_n,~\mathbf{B}_n,~\mathbf{C}_n$ and $\mathbf{G}_2$ can be represented by a finite Weyl group. In particular, at each blow-up point, after a sequence of bubbling steps (via scaling) is performed, the transformation of the local mass at each step corresponds to the action of an element in the Weyl group. In this article, we present the results in the same spirit for the affine $\mathbf{B}_2^{(1)}$ Toda system with singularities. Compared with the Toda system with simple Lie algebras, the computation of local masses is more challenging due to the infinite number of elements of the {affine Weyl group of type $\mathbf{B}_{2}^{(1)}$}. In order to give an explicit expression for the local mass formula we introduce two free integers and write down all the possibilities into 8 types. This shows a striking difference to previous results on Toda systems with simple Lie algebras. The main result of this article seems to provide the first major advance in understanding the relation between the blow-up analysis of affine Toda system and the {affine Weyl group} of the associated Lie algebras.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Understanding the Dynamics of DNNs Using Graph Modularity

There are good arguments to support the claim that deep neural networks (DNNs) capture better feature representations than the previous hand-crafted feature engineering, which leads to a significant performance improvement. In this paper, we move a tiny step towards understanding the dynamics of feature representations over layers. Specifically, we model the process of class separation of intermediate representations in pre-trained DNNs as the evolution of communities in dynamic graphs. Then, we introduce modularity, a generic metric in graph theory, to quantify the evolution of communities. In the preliminary experiment, we find that modularity roughly tends to increase as the layer goes deeper and the degradation and plateau arise when the model complexity is great relative to the dataset. Through an asymptotic analysis, we prove that modularity can be broadly used for different applications. For example, modularity provides new insights to quantify the difference between feature representations. More crucially, we demonstrate that the degradation and plateau in modularity curves represent redundant layers in DNNs and can be pruned with minimal impact on performance, which provides theoretical guidance for layer pruning. Our code is available at https://github.com/yaolu-zjut/Dynamic-Graphs-Construction.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Point Cloud-Based Method for Automatic Groove Detection and Trajectory Generation of Robotic Arc Welding Tasks

In this paper, in order to pursue high-efficiency robotic arc welding tasks, we propose a method based on point cloud acquired by an RGB-D sensor. The method consists of two parts: welding groove detection and 3D welding trajectory generation. The actual welding scene could be displayed in 3D point cloud format. Focusing on the geometric feature of the welding groove, the detection algorithm is capable of adapting well to different welding workpieces with a V-type welding groove. Meanwhile, a 3D welding trajectory involving 6-DOF poses of the welding groove for robotic manipulator motion is generated. With an acceptable error in trajectory generation, the robotic manipulator could drive the welding torch to follow the trajectory and execute welding tasks. In this paper, details of the integrated robotic system are also presented. Experimental results prove application value of the presented welding robotic system.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Classification of finite Morse index solutions of higher-order Gelfand-Liouville equation

We classify finite Morse index solutions of the following Gelfand-Liouville equation \begin{equation*} (-Δ)^{s} u= e^u \ \ \text{in} \ \ \mathbb{R}^n, \end{equation*} for $1<s<2$ and $s=2$ via a novel monotonicity formula and technical blow-down analysis. We show that the above equation does not admit any finite Morse index solution with $(-Δ)^{s/2} u$ vanishes at infinity provided $n>2s$ and \begin{equation*} \label{1.condition} \frac{ Γ(\frac{n+2s}{4})^2 }{ Γ(\frac{n-2s}{4})^2} < \frac{Γ(\frac{n}{2}) Γ(1+s)}{ Γ(\frac{n-2s}{2})}, \end{equation*} where $Γ$ is the classical Gamma function. The cases of $s=1$ and $s=2$ are settled by Dancer and Farina \cite{df,d} and Dupaigne et al. \cite{dggw}, respectively, using Moser iteration arguments established by Crandall and Rabinowitz \cite{CR}. The case of $0<s<1$ is established by Hyder-Yang in \cite{hy} applying arguments provided in \cite{ddw,fw}.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Classification of stable solutions to a non-local Gelfand-Liouville equation

We study finite Morse index solutions to the non-local Gelfand-Liouville problem $$ (-Δ)^su=e^u\quad\mathrm{in}\quad \mathbb{R}^n,$$ for every $s\in(0,1)$ and $n>2s$. Precisely, we prove non-existence of finite Morse index solutions whenever the singular solution $$u_{n,s}(x)=-2s\log|x|+\log \left(2^{2s}\frac{Γ(\frac{n}{2})Γ(1+s)}{Γ(\frac{n-2s}{2})}\right)$$ is unstable.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Event Enhanced High-Quality Image Recovery

With extremely high temporal resolution, event cameras have a large potential for robotics and computer vision. However, their asynchronous imaging mechanism often aggravates the measurement sensitivity to noises and brings a physical burden to increase the image spatial resolution. To recover high-quality intensity images, one should address both denoising and super-resolution problems for event cameras. Since events depict brightness changes, with the enhanced degeneration model by the events, the clear and sharp high-resolution latent images can be recovered from the noisy, blurry and low-resolution intensity observations. Exploiting the framework of sparse learning, the events and the low-resolution intensity observations can be jointly considered. Based on this, we propose an explainable network, an event-enhanced sparse learning network (eSL-Net), to recover the high-quality images from event cameras. After training with a synthetic dataset, the proposed eSL-Net can largely improve the performance of the state-of-the-art by 7-12 dB. Furthermore, without additional training process, the proposed eSL-Net can be easily extended to generate continuous frames with frame-rate as high as the events.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Implicit Euler ODE Networks for Single-Image Dehazing

Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem. Recently, many works indicate that the ResNet can be considered as the explicit Euler forward approximation of an ordinary differential equation (ODE). In this paper, we extend the explicit forward approximation to the implicit backward counterpart, which can be realized via a recursive neural network, named IM-block. Given that, we propose an efficient end-to-end multi-level implicit network (MI-Net) for the single image dehazing problem. Moreover, multi-level fusing (MLF) mechanism and residual channel attention block (RCA-block) are adopted to boost performance of our network. Experiments on several dehazing benchmark datasets demonstrate that our method outperforms existing methods and achieves the state-of-the-art performance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Matching Neuromorphic Events and Color Images via Adversarial Learning

The event camera has appealing properties: high dynamic range, low latency, low power consumption and low memory usage, and thus provides complementariness to conventional frame-based cameras. It only captures the dynamics of a scene and is able to capture almost &#34;continuous&#34; motion. However, different from frame-based camera that reflects the whole appearance as scenes are, the event camera casts away the detailed characteristics of objects, such as texture and color. To take advantages of both modalities, the event camera and frame-based camera are combined together for various machine vision tasks. Then the cross-modal matching between neuromorphic events and color images plays a vital and essential role. In this paper, we propose the Event-Based Image Retrieval (EBIR) problem to exploit the cross-modal matching task. Given an event stream depicting a particular object as query, the aim is to retrieve color images containing the same object. This problem is challenging because there exists a large modality gap between neuromorphic events and color images. We address the EBIR problem by proposing neuromorphic Events-Color image Feature Learning (ECFL). Particularly, the adversarial learning is employed to jointly model neuromorphic events and color images into a common embedding space. We also contribute to the community N-UKbench and EC180 dataset to promote the development of EBIR problem. Extensive experiments on our datasets show that the proposed method is superior in learning effective modality-invariant representation to link two different modalities.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences

Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO\&VIO) techniques are well-developed for state estimation but with inevitable accumulated drifts and pose jumps upon loop closure. To overcome these problems, we propose an efficient monocular camera localization method in prior LiDAR maps using direct 2D-3D line correspondences. To handle the appearance differences and modality gaps between LiDAR point clouds and images, geometric 3D lines are extracted offline from LiDAR maps while robust 2D lines are extracted online from video sequences. With the pose prediction from VIO, we can efficiently obtain coarse 2D-3D line correspondences. Then the camera poses and 2D-3D correspondences are iteratively optimized by minimizing the projection error of correspondences and rejecting outliers. Experimental results on the EurocMav dataset and our collected dataset demonstrate that the proposed method can efficiently estimate camera poses without accumulated drifts or pose jumps in structured environments.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Nonlinear anomalous Hall effect for Néel vector detection

Antiferromagnetic (AFM) spintronics exploits the Néel vector as a state variable for novel spintronic devices. Recent studies have shown that the field-like and antidamping spin-orbit torques (SOT) can be used to switch the Néel vector in antiferromagnets with proper symmetries. However, the precise detection of the Néel vector remains a challenging problem. In this letter, we predict that the nonlinear anomalous Hall effect (AHE) can be used to detect the Néel vector in most compensated antiferromagnets supporting the antidamping SOT. We show that the magnetic crystal group symmetry of these antiferromagnets combined with spin-orbit coupling produce a sizable Berry curvature dipole and hence the nonlinear AHE. As a specific example, we consider half-Heusler alloy CuMnSb, which Néel vector can be switched by the antidamping SOT. Based on density functional theory calculations, we show that the nonlinear AHE in CuMnSb results in a measurable Hall voltage under conventional experimental conditions. The strong dependence of the Berry curvature dipole on the Néel vector orientation provides a new detection scheme of the Néel vector based on the nonlinear AHE. Our predictions enrich the material platform for studying non-trivial phenomena associated with the Berry curvature and broaden the range of materials useful for AFM spintronics.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On stable and finite Morse index solutions of the fractional Toda system

We develop a monotonicity formula for solutions of the fractional Toda system $$ (-Δ)^s f_α= e^{-(f_{α+1}-f_α)} - e^{-(f_α-f_{α-1})} \quad \text{in} \ \ \mathbb R^n,$$ when $0<s<1$, $α=1,\cdots,Q$, $f_0=-\infty$, $f_{Q+1}=\infty$ and $Q \ge2$ is the number of equations in this system. We then apply this formula, technical integral estimates, classification of stable homogeneous solutions, and blow-down analysis arguments to establish Liouville type theorems for finite Morse index (and stable) solutions of the above system when $n > 2s$ and $$ \dfrac{Γ(\frac{n}{2})Γ(1+s)}{Γ(\frac{n-2s}{2})} \frac{Q(Q-1)}{2} > \frac{ Γ(\frac{n+2s}{4})^2 }{ Γ(\frac{n-2s}{4})^2} . $$ Here, $Γ$ is the Gamma function. When $Q=2$, the above equation is the classical (fractional) Gelfand-Liouville equation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On stable and finite Morse index solutions of the nonlocal Hénon-Gelfand-Liouville equation

We consider the nonlocal Hénon-Gelfand-Liouville problem $$ (-Δ)^s u = |x|^a e^u\quad\mathrm{in}\quad \mathbb R^n, $$ for every $s\in(0,1)$, $a>0$ and $n>2s$. We prove a monotonicity formula for solutions of the above equation using rescaling arguments. We apply this formula together with blow-down analysis arguments and technical integral estimates to establish non-existence of finite Morse index solutions when $$\dfrac{Γ(\frac n2)Γ(s)}{Γ(\frac{n-2s}{2})}\left(s+\frac a2\right)> \dfrac{Γ^2(\frac{n+2s}{4})}{Γ^2(\frac{n-2s}{4})}.$$

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Semantic Change Pattern Analysis

Change detection is an important problem in vision field, especially for aerial images. However, most works focus on traditional change detection, i.e., where changes happen, without considering the change type information, i.e., what changes happen. Although a few works have tried to apply semantic information to traditional change detection, they either only give the label of emerging objects without taking the change type into consideration, or set some kinds of change subjectively without specifying semantic information. To make use of semantic information and analyze change types comprehensively, we propose a new task called semantic change pattern analysis for aerial images. Given a pair of co-registered aerial images, the task requires a result including both where and what changes happen. We then describe the metric adopted for the task, which is clean and interpretable. We further provide the first well-annotated aerial image dataset for this task. Extensive baseline experiments are conducted as reference for following works. The aim of this work is to explore high-level information based on change detection and facilitate the development of this field with the publicly available dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Single Image Deraining with Continuous Rain Density Estimation

Single image deraining (SIDR) often suffers from over/under deraining due to the nonuniformity of rain densities and the variety of raindrop scales. In this paper, we propose a \textbf{\it co}ntinuous \textbf{\it de}nsity guided network (CODE-Net) for SIDR. Particularly, it is composed of { a rain {\color{black}streak} extractor and a denoiser}, where the convolutional sparse coding (CSC) is exploited to filter out noises from the extracted rain streaks. Inspired by the reweighted iterative soft-threshold for CSC, we address the problem of continuous rain density estimation by learning the weights with channel attention blocks from sparse codes. We further {\color{black}develop} a multiscale strategy to depict rain streaks appearing at different scales. Experiments on synthetic and real-world data demonstrate the superiority of our methods over recent {\color{black}state of the arts}, in terms of both quantitative and qualitative results. Additionally, instead of quantizing rain density with several levels, our CODE-Net can provide continuous-valued estimations of rain densities, which is more desirable in real applications.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Structure-Aware Network for Lane Marker Extraction with Dynamic Vision Sensor

Lane marker extraction is a basic yet necessary task for autonomous driving. Although past years have witnessed major advances in lane marker extraction with deep learning models, they all aim at ordinary RGB images generated by frame-based cameras, which limits their performance in extreme cases, like huge illumination change. To tackle this problem, we introduce Dynamic Vision Sensor (DVS), a type of event-based sensor to lane marker extraction task and build a high-resolution DVS dataset for lane marker extraction. We collect the raw event data and generate 5,424 DVS images with a resolution of 1280$\times$800 pixels, the highest one among all DVS datasets available now. All images are annotated with multi-class semantic segmentation format. We then propose a structure-aware network for lane marker extraction in DVS images. It can capture directional information comprehensively with multidirectional slice convolution. We evaluate our proposed network with other state-of-the-art lane marker extraction models on this dataset. Experimental results demonstrate that our method outperforms other competitors. The dataset is made publicly available, including the raw event data, accumulated images and labels.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Local uniqueness and non-degeneracy of blow up solutions of mean field equations with singular data

We are concerned with the mean field equation with singular data on bounded domains. Under suitable non-degeneracy conditions we prove local uniqueness and non-degeneracy of bubbling solutions blowing up at singular points. The proof is based on sharp estimates for bubbling solutions of singular mean field equations and suitably defined Pohozaev-type identities.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Longitudinal relaxation of a nitrogen-vacancy center in a spin bath by generalized cluster-correlation expansion method

We theoretically study the longitudinal relaxation of a nitrogen-vacancy (NV) center surrounded by a 13C nuclear spin bath in diamond. By incorporating electron spin in the cluster, we generalize the cluster-correlation expansion (CCE) to theoretically simulate the population dynamics of electron spin of NV center. By means of the generalized CCE, we numerically demonstrate the decay process of electronic state induced by cross relaxation at the ambient temperature. It is shown that the CCE method is not only capable of describing pure-dephasing effect at large-detuning regime, but it can also simulate the quantum dynamics of populations in the nearly-resonant regime.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Mean field equations on tori: existence and uniqueness of evenly symmetric blow-up solutions

We are concerned with the blow-up analysis of mean field equations. It has been proven in [6] that solutions blowing-up at the same non-degenerate blow-up set are unique. On the other hand, the authors in [18] show that solutions with a degenerate blow-up set are in general non-unique. In this paper we first prove that evenly symmetric solutions on a flat torus with a degenerate two-point blow-up set are unique. In the second part of the paper we complete the analysis by proving the existence of such blow-up solutions by using a Lyapunov-Schmidt reduction method. Moreover, we deduce that all evenly symmetric blow-up solutions come from one-point blow-up solutions of the mean field equation on a &#34;half&#34; torus.

0 citations0 reviewsNo code linkedOpen access
preprint2018arXiv

Wave equations associated to Liouville-type problems: global existence in time and blow up criteria

We are concerned with wave equations associated to some Liouville-type problems on compact surfaces, focusing on sinh-Gordon equation and general Toda systems. Our aim is on one side to develop the analysis for wave equations associated to the latter problems and second, to substantially refine the analysis initiated in [11] concerning the mean field equation. In particular, by exploiting the variational analysis recently derived for Liouville-type problems we prove global existence in time for the sub-critical case and we give general blow up criteria for the super-critical and critical case. The strategy is mainly based on fixed point arguments and improved versions of the Moser-Trudinger inequality.

0 citations0 reviewsNo code linkedOpen access