BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Xingang Wang

Xingang Wang appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
nlin.CDComputer Visionnlin.AONetworking and Internet Architecturephysics.soc-phMachine LearningNeurons and Cognitionnlin.PScond-mat.dis-nnNeural and Evolutionary ComputingSocial and Information Networks

Catalog footprint

What is connected

21works
11topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

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

Published work

21 published item(s)

preprint2026arXiv

Inferring bifurcation diagrams of two distinct chaotic systems by a single machine

We propose a dual-channel reservoir-computing scheme for inferring the dynamics of two distinct chaotic systems with a single machine. By augmenting a standard reservoir with a system-label channel and a parameter-control channel, the machine can be trained from time series collected from a few sampled states of the two systems. We show that the trained machine not only predicts the short-time evolution of the sampled states, but also reproduces the long-term statistical properties of unseen states, thereby enabling reconstruction of the bifurcation diagrams of both systems from partial observations. The effectiveness of the scheme is demonstrated for the Lorenz and Rössler systems in numerical simulations and for the Chua and Rossler circuits in experiments. Functional-network analysis further shows that the two target systems are encoded by distinct dynamical patterns in the reservoir. These results extend multifunctional and parameter-aware reservoir computing, and provide a route to data-driven inference of multiple nonlinear systems using a single machine.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning

Self-supervised monocular methods can efficiently learn depth information of weakly textured surfaces or reflective objects. However, the depth accuracy is limited due to the inherent ambiguity in monocular geometric modeling. In contrast, multi-frame depth estimation methods improve the depth accuracy thanks to the success of Multi-View Stereo (MVS), which directly makes use of geometric constraints. Unfortunately, MVS often suffers from texture-less regions, non-Lambertian surfaces, and moving objects, especially in real-world video sequences without known camera motion and depth supervision. Therefore, we propose MOVEDepth, which exploits the MOnocular cues and VElocity guidance to improve multi-frame Depth learning. Unlike existing methods that enforce consistency between MVS depth and monocular depth, MOVEDepth boosts multi-frame depth learning by directly addressing the inherent problems of MVS. The key of our approach is to utilize monocular depth as a geometric priority to construct MVS cost volume, and adjust depth candidates of cost volume under the guidance of predicted camera velocity. We further fuse monocular depth and MVS depth by learning uncertainty in the cost volume, which results in a robust depth estimation against ambiguity in multi-view geometry. Extensive experiments show MOVEDepth achieves state-of-the-art performance: Compared with Monodepth2 and PackNet, our method relatively improves the depth accuracy by 20\% and 19.8\% on the KITTI benchmark. MOVEDepth also generalizes to the more challenging DDAD benchmark, relatively outperforming ManyDepth by 7.2\%. The code is available at https://github.com/JeffWang987/MOVEDepth.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

HFT: Lifting Perspective Representations via Hybrid Feature Transformation

Autonomous driving requires accurate and detailed Bird's Eye View (BEV) semantic segmentation for decision making, which is one of the most challenging tasks for high-level scene perception. Feature transformation from frontal view to BEV is the pivotal technology for BEV semantic segmentation. Existing works can be roughly classified into two categories, i.e., Camera model-Based Feature Transformation (CBFT) and Camera model-Free Feature Transformation (CFFT). In this paper, we empirically analyze the vital differences between CBFT and CFFT. The former transforms features based on the flat-world assumption, which may cause distortion of regions lying above the ground plane. The latter is limited in the segmentation performance due to the absence of geometric priors and time-consuming computation. In order to reap the benefits and avoid the drawbacks of CBFT and CFFT, we propose a novel framework with a Hybrid Feature Transformation module (HFT). Specifically, we decouple the feature maps produced by HFT for estimating the layout of outdoor scenes in BEV. Furthermore, we design a mutual learning scheme to augment hybrid transformation by applying feature mimicking. Notably, extensive experiments demonstrate that with negligible extra overhead, HFT achieves a relative improvement of 13.3% on the Argoverse dataset and 16.8% on the KITTI 3D Object datasets compared to the best-performing existing method. The codes are available at https://github.com/JiayuZou2020/HFT.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation

Albeit with varying degrees of progress in the field of Semi-Supervised Semantic Segmentation, most of its recent successes are involved in unwieldy models and the lightweight solution is still not yet explored. We find that existing knowledge distillation techniques pay more attention to pixel-level concepts from labeled data, which fails to take more informative cues within unlabeled data into account. Consequently, we offer the first attempt to provide lightweight SSSS models via a novel multi-granularity distillation (MGD) scheme, where multi-granularity is captured from three aspects: i) complementary teacher structure; ii) labeled-unlabeled data cooperative distillation; iii) hierarchical and multi-levels loss setting. Specifically, MGD is formulated as a labeled-unlabeled data cooperative distillation scheme, which helps to take full advantage of diverse data characteristics that are essential in the semi-supervised setting. Image-level semantic-sensitive loss, region-level content-aware loss, and pixel-level consistency loss are set up to enrich hierarchical distillation abstraction via structurally complementary teachers. Experimental results on PASCAL VOC2012 and Cityscapes reveal that MGD can outperform the competitive approaches by a large margin under diverse partition protocols. For example, the performance of ResNet-18 and MobileNet-v2 backbone is boosted by 11.5% and 4.6% respectively under 1/16 partition protocol on Cityscapes. Although the FLOPs of the model backbone is compressed by 3.4-5.3x (ResNet-18) and 38.7-59.6x (MobileNetv2), the model manages to achieve satisfactory segmentation results.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

Learning-based Multi-View Stereo (MVS) methods warp source images into the reference camera frustum to form 3D volumes, which are fused as a cost volume to be regularized by subsequent networks. The fusing step plays a vital role in bridging 2D semantics and 3D spatial associations. However, previous methods utilize extra networks to learn 2D information as fusing cues, underusing 3D spatial correlations and bringing additional computation costs. Therefore, we present MVSTER, which leverages the proposed epipolar Transformer to learn both 2D semantics and 3D spatial associations efficiently. Specifically, the epipolar Transformer utilizes a detachable monocular depth estimator to enhance 2D semantics and uses cross-attention to construct data-dependent 3D associations along epipolar line. Additionally, MVSTER is built in a cascade structure, where entropy-regularized optimal transport is leveraged to propagate finer depth estimations in each stage. Extensive experiments show MVSTER achieves state-of-the-art reconstruction performance with significantly higher efficiency: Compared with MVSNet and CasMVSNet, our MVSTER achieves 34% and 14% relative improvements on the DTU benchmark, with 80% and 51% relative reductions in running time. MVSTER also ranks first on Tanks&Temples-Advanced among all published works. Code is released at https://github.com/JeffWang987.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Criticality in Reservoir Computer of Coupled Phase Oscillators

Accumulating evidences show that the cerebral cortex is operating near a critical state featured by power-law size distribution of neural avalanche activities, yet evidence of this critical state in artificial neural networks mimicking the cerebral cortex is lacking. Here we design an artificial neural network of coupled phase oscillators and, by the technique of reservoir computing in machine learning, train it for predicting chaos. It is found that when the machine is properly trained, oscillators in the reservoir are synchronized into clusters whose sizes follow a power-law distribution. This feature, however, is absent when the machine is poorly trained. Additionally, it is found that despite the synchronization degree of the original network, once properly trained, the reservoir network is always developed to the same critical state, exemplifying the "attractor" nature of this state in machine learning. The generality of the results is verified in different reservoir models and by different target systems, and it is found that the scaling exponent of the distribution is independent on the reservoir details and the bifurcation parameter of the target system, but is modified when the dynamics of the target system is changed to a different type. The findings shed lights on the nature of machine learning, and are helpful to the design of high-performance machine in physical systems.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation

Most recent semi-supervised video object segmentation (VOS) methods rely on fine-tuning deep convolutional neural networks online using the given mask of the first frame or predicted masks of subsequent frames. However, the online fine-tuning process is usually time-consuming, limiting the practical use of such methods. We propose a directional deep embedding and appearance learning (DDEAL) method, which is free of the online fine-tuning process, for fast VOS. First, a global directional matching module, which can be efficiently implemented by parallel convolutional operations, is proposed to learn a semantic pixel-wise embedding as an internal guidance. Second, an effective directional appearance model based statistics is proposed to represent the target and background on a spherical embedding space for VOS. Equipped with the global directional matching module and the directional appearance model learning module, DDEAL learns static cues from the labeled first frame and dynamically updates cues of the subsequent frames for object segmentation. Our method exhibits state-of-the-art VOS performance without using online fine-tuning. Specifically, it achieves a J & F mean score of 74.8% on DAVIS 2017 dataset and an overall score G of 71.3% on the large-scale YouTube-VOS dataset, while retaining a speed of 25 fps with a single NVIDIA TITAN Xp GPU. Furthermore, our faster version runs 31 fps with only a little accuracy loss. Our code and trained networks are available at https://github.com/YingjieYin/Directional-Deep-Embedding-and-Appearance-Learning-for-Fast-Video-Object-Segmentation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Dynamic Routing for Semantic Segmentation

Recently, numerous handcrafted and searched networks have been applied for semantic segmentation. However, previous works intend to handle inputs with various scales in pre-defined static architectures, such as FCN, U-Net, and DeepLab series. This paper studies a conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing. The proposed framework generates data-dependent routes, adapting to the scale distribution of each image. To this end, a differentiable gating function, called soft conditional gate, is proposed to select scale transform paths on the fly. In addition, the computational cost can be further reduced in an end-to-end manner by giving budget constraints to the gating function. We further relax the network level routing space to support multi-path propagations and skip-connections in each forward, bringing substantial network capacity. To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space. Extensive experiments are conducted on Cityscapes and PASCAL VOC 2012 to illustrate the effectiveness of the dynamic framework. Code is available at https://github.com/yanwei-li/DynamicRouting.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Long-term prediction of chaotic systems with recurrent neural networks

Reservoir computing systems, a class of recurrent neural networks, have recently been exploited for model-free, data-based prediction of the state evolution of a variety of chaotic dynamical systems. The prediction horizon demonstrated has been about half dozen Lyapunov time. Is it possible to significantly extend the prediction time beyond what has been achieved so far? We articulate a scheme incorporating time-dependent but sparse data inputs into reservoir computing and demonstrate that such rare "updates" of the actual state practically enable an arbitrarily long prediction horizon for a variety of chaotic systems. A physical understanding based on the theory of temporal synchronization is developed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Transfer learning of chaotic systems

Can a neural network trained by the time series of system A be used to predict the evolution of system B? This problem, knowing as transfer learning in a broad sense, is of great importance in machine learning and data mining, yet has not been addressed for chaotic systems. Here we investigate transfer learning of chaotic systems from the perspective of synchronization-based state inference, in which a reservoir computer trained by chaotic system A is used to infer the unmeasured variables of chaotic system B, while A is different from B in either parameter or dynamics. It is found that if systems A and B are different in parameter, the reservoir computer can be well synchronized to system B. However, if systems A and B are different in dynamics, the reservoir computer fails to synchronize with system B in general. Knowledge transfer along a chain of coupled reservoir computers is also studied, and it is found that, although the reservoir computers are trained by different systems, the unmeasured variables of the driving system can be successfully inferred by the remote reservoir computer. Finally, by an experiment of chaotic pendulum, we show that the knowledge learned from the modeling system can be used to predict the evolution of the experimental system.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Evoking complex neuronal networks by stimulating a single neuron

The dynamical responses of complex neuronal networks to external stimulus injected on a \emph{single} neuron are investigated. Stimulating the largest-degree neuron in the network, it is found that as the intensity of the stimulus increases, the network will be transiting from the resting to firing states and then restoring to the resting state, showing a bounded firing region in the parameter space. Furthermore, it is found that as the coupling strength decreases, the firing region is gradually expanded and, at the weak couplings, separated into disconnected subregions. By a simplified network model, we conduct a detail analysis on the bifurcation diagram of the network dynamics in the two-dimensional parameter space spanned by stimulating intensity and coupling strength, and, by introducing a new coefficient named effective stimulus, explore the mechanisms of the modified firing region. It is revealed that the coupling strength and stimulating intensity are equally important in evoking the network, but with different mechanisms. Specifically, the effective stimuli are \emph{shifted up} globally with the increase of the stimulating intensity, while are \emph{drawn closer} with the increase of the coupling strength. The dynamical responses of small-world and random complex networks to external stimulus injected on the largest-degree neuron are also investigated, which confirm the generality of the observed phenomena.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Growth, collapse, and self-organized criticality in complex networks

To understand how certain dynamical behaviors can or cannot persist as the underlying network grows is a problem of increasing importance in complex dynamical systems as well as sustainability science and engineering. We address the question of whether a complex network of nonlinear oscillators can maintain its synchronization stability as it expands or grows. A network in the real world can never be completely synchronized due to noise and/or external disturbances. This is especially the case when, mathematically, the transient synchronous state during the growth process becomes marginally stable, as a local perturbation can trigger a rapid deviation of the system from the vicinity of the synchronous state. In terms of the nodal dynamics, a large scale avalanche over the entire network can be triggered in the sense that the individual nodal dynamics diverge from the synchronous state in a cascading manner within a short time period. Because of the high dimensionality of the networked system, the transient process for the system to recover to the synchronous state can be extremely long. Introducing a tolerance threshold to identify the desynchronized nodes, we find that, after an initial stage of linear growth, the network typically evolves into a critical state where the addition of a single new node can cause a group of nodes to lose synchronization, leading to synchronization collapse for the entire network. A statistical analysis indicates that, the distribution of the size of the collapse is approximately algebraic (power law), regardless of the fluctuations in the system parameters. This is indication of the emergence of self-organized criticality. We demonstrate the generality of the phenomenon of synchronization collapse using a variety of complex network models, and uncover the underlying dynamical mechanism through an eigenvector analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Improving Performance of IEEE 802.11 by a Dynamic Control Backoff Algorithm Under Unsaturated Traffic Loads

The IEEE 802.11 backoff algorithm is very important for controlling system throughput over contentionbased wireless networks. For this reason, there are many studies on wireless network performance focus on developing backoff algorithms. However, most existing models are based on saturated traffic loads, which are not a real representation of actual network conditions. In this paper, a dynamic control backoff time algorithm is proposed to enhance both delay and throughput performance of the IEEE 802.11 distributed coordination function. This algorithm considers the distinction between high and low traffic loads in order to deal with unsaturated traffic load conditions. In particular, the equilibrium point analysis model is used to represent the algorithm under various traffic load conditions. Results of extensive simulation experiments illustrate that the proposed algorithm yields better performance throughput and a better average transmission packet delay than related algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Controlling synchronous patterns in complex networks

Although the set of permutation symmetries of a complex network can be very large, few of the symmetries give rise to stable synchronous patterns. Here we present a new framework and develop techniques for controlling synchronization patterns in complex network of coupled chaotic oscillators. Specifically, according to the network permutation symmetry, we design a small-size and weighted network, namely the control network, and use it to control the large-size complex network by means of pinning coupling. We argue mathematically that for \emph{any} of the network symmetries, there always exists a critical pinning strength beyond which the unstable synchronous pattern associated to this symmetry can be stabilized. The feasibility of the control method is verified by numerical simulations of both artificial and real-work networks, and is demonstrated by experiment of coupled chaotic circuits. Our studies pave a way to the control of dynamical patterns in complex networks.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Inducing chimera-synchronization in symmetric complex networks

In a recent study of chaos synchronization in symmetric complex networks [Pecora \textit{et al}., Nat. Commun. {\bf 5}, 4079 (2014)], it is found that stable synchronous clusters may coexist with many non-synchronous nodes in the asynchronous regime, resembling the chimera state observed in regular networks of non-locally coupled periodic oscillators. Although of practical significance, this new type of state, namely the chimera-synchronization state, is hardly generated for the general complex networks, due to either the topological instabilities or the weak coupling strength. Here, based on the strategy of pinning coupling, we propose an effective method for inducing chimera-synchronization in symmetric complex network of coupled chaotic oscillators. We are able to argue mathematically that, by pinning a group of nodes satisfying permutation symmetry, there always exits a critical pinning strength beyond which the unstable chimera-synchronization states can be successfully induced. The feasibility and efficiency of the control method are verified by numerical simulations of both artificial and real-world complex networks, with the numerical results well fitted by the theoretical predictions.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Estimation of Medium Access Control Layer Packet Delay Distribution for IEEE 802.11

The most important standard in wireless local area networks is IEEE 802.11. This is why much of the research work for the enhancement of wireless network is usually based on the behavior of IEEE 802.11 protocol. However, some of the ways in which IEEE 802.11 medium access control layer behaves is still unreliable to guarantee quality of service. For instance, medium access control layer packet delay, jitter and packet loss rate still remain a challenge. The main objective of this research is to propose an accurate estimation of the medium access control layer packet delay distribution for IEEE 802.11. This estimation considers the differences between busy probability and collision probability. These differences are employed to achieve a more accurate estimation. Finally, the proposed model and simulation are implemented and validated - using MATLAB program for the purpose of simulation, and Maple program to undertake the calculation of the equations.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Onset of Synchronization in Weighted Complex Networks: the Effect of Weight-Degree Correlation

By numerical simulations, we investigate the onset of synchronization of networked phase oscillators under two different weighting schemes. In scheme-I, the link weights are correlated to the product of the degrees of the connected nodes, so this kind of networks is named as the weight-degree correlated (WDC) network. In scheme-II, the link weights are randomly assigned to each link regardless of the node degrees, so this kind of networks is named as the weight-degree uncorrelated (WDU) network. Interestingly, it is found that by increasing a parameter that governs the weight distribution, the onset of synchronization in WDC network is monotonically enhanced, while in WDU network there is a reverse in the synchronization performance. We investigate this phenomenon from the viewpoint of gradient network, and explain the contrary roles of coupling gradient on network synchronization: gradient promotes synchronization in WDC network, while deteriorates synchronization in WDU network. The findings highlight the fact that, besides the link weight, the correlation between the weight and node degree is also important to the network dynamics.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

On the pinning strategy of complex networks

In pinning control of complex networks, a tacit believing is that the system dynamics will be better controlled by pinning the large-degree nodes than the small-degree ones. Here, by changing the number of pinned nodes, we find that, when a significant fraction of the network nodes are pinned, pinning the small-degree nodes could generally have a higher performance than pinning the large-degree nodes. We demonstrate this interesting phenomenon on a variety of complex networks, and analyze the underlying mechanisms by the model of star networks. By changing the network properties, we also find that, comparing to densely connected homogeneous networks, the advantage of the small-degree pinning strategy is more distinct in sparsely connected heterogenous networks.

0 citations0 reviewsNo code linkedOpen access
preprint2009arXiv

Evolutionary Subnetworks in Complex Systems

Links in a practical network may have different functions, which makes the original network a combination of some functional subnetworks. Here, by a model of coupled oscillators, we investigate how such functional subnetworks are evolved and developed according to the network structure and dynamics. In particular, we study the case of evolutionary clustered networks in which the function of each link (either attractive or repulsive coupling) is updated by the local dynamics. It is found that, during the process of system evolution, the network is gradually stabilized into a particular form in which the attractive (repulsive) subnetwork consists only the intralinks (interlinks). Based on the properties of subnetwork evolution, we also propose a new algorithm for network partition which is distinguished by the convenient operation and fast computing speed.

0 citations0 reviewsNo code linkedOpen access
preprint2008arXiv

Transition to amplitude death in scale-free networks

Transition to amplitude death in scale-free networks of nonlinear oscillators is investigated. As the coupling strength increases, the network will undergo three stages in approaching to the state of complete amplitude death. The first stage is featured by a \emph{"stair-like"} distribution of the node amplitude, and the transition is accomplished by a \emph{hierarchical death} of the amplitude stairs. The second and third stages are characterized by, respectively, a continuing elimination of the synchronous clusters and a fast death of the non-synchronized nodes.

0 citations0 reviewsNo code linkedOpen access
preprint2007arXiv

Enhancing synchronization in complex networks of coupled phase oscillators

By a model of coupled phase oscillators, we show analytically how synchronization in {\em non-identical} complex networks can be enhanced by introducing a proper gradient into the couplings. It is found that, by pointing the gradient from the large-degree to the small-degree nodes on each link, increasing the gradient strength will bring forward the {\em onset} of network synchronization monotonically, and, under the same gradient strength, heterogeneous networks are more synchronizable than homogeneous networks. These findings are verified by extensive simulations.

0 citations0 reviewsNo code linkedOpen access