arXiv subjects

Ming Tang

Publications and source records attributed to Ming Tang.

At least 163 records · Page 9Linked to original sources

arXiv2022

Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification

Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identification (Re-ID). To alleviate the adverse effect of noisy pseudo labels, the existing methods either abandon unreliable labels or refine the pseudo labels via mutual learning or label propagation. However, a great many erroneous labels are still accumulated because these methods mostly adopt traditional unsupervised clustering algorithms which rely on certain assumptions on data distribution and fail to capture the distribution of complex real-world data. In this paper, we propose the plug-and-play graph-based pseudo label correction network (GLC) to refine the pseudo labels in the manner of supervised clustering. GLC is trained to perceive the varying data distribution at each epoch of the self-training with the supervision of initial pseudo labels generated by any clustering method. It can learn to rectify the initial noisy labels by means of the relationship constraints between samples on the k Nearest Neighbor (kNN) graph and early-stop training strategy. Specifically, GLC learns to aggregate node features from neighbors and predict whether the nodes should be linked on the graph. Besides, GLC is optimized with 'early stop' before the noisy labels are severely memorized to prevent overfitting to noisy pseudo labels. Consequently, GLC improves the quality of pseudo labels though the supervision signals contain some noise, leading to better Re-ID performance. Extensive experiments in USL and UDA person Re-ID on Market-1501 and MSMT17 show that our method is widely compatible with various clustering-based methods and promotes the state-of-the-art performance consistently.

cs.CV↗

arXiv2022

A modified weak Galerkin method for $\boldsymbol{H}(\mathrm{curl})$-elliptic problem

In this paper, we design and analysis a modified weak Galerkin (MWG) finite element method for $\boldsymbol{H}(\mathrm{curl})-$elliptic problem. We first introduce a new discrete weak curl operator and the MWG finite element space. The modified weak Galerkin method does not require the penalty parameter by comparing with traditional DG methods. We prove optimal error estimates in energy norm. At last, we provide the numerical results to confirm these theoretical results.

math.NA↗

arXiv2022

UniVIP: A Unified Framework for Self-Supervised Visual Pre-training

Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the scene and instances, as well as the semantic difference of instances in the scene. To address the above problems, we propose a Unified Self-supervised Visual Pre-training (UniVIP), a novel self-supervised framework to learn versatile visual representations on either single-centric-object or non-iconic dataset. The framework takes into account the representation learning at three levels: 1) the similarity of scene-scene, 2) the correlation of scene-instance, 3) the discrimination of instance-instance. During the learning, we adopt the optimal transport algorithm to automatically measure the discrimination of instances. Massive experiments show that UniVIP pre-trained on non-iconic COCO achieves state-of-the-art transfer performance on a variety of downstream tasks, such as image classification, semi-supervised learning, object detection and segmentation. Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2.5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.

cs.CV↗

arXiv2022

Beyond the Limitation of Pulse Width in Optical Time-domain Reflectometry

Optical time-domain reflectometry (OTDR) is the basis for distributed time-domain optical fiber sensing techniques. By injecting pulse light into an optical fiber, the distance information of an event can be obtained based on the time of light flight. The minimum distinguishable event separation along the fiber length is called the spatial resolution, which is determined by the optical pulse width. By reducing the pulse width, the spatial resolution can be improved. However, at the same time, the signal-to-noise ratio of the system is degraded, and higher speed equipment is required. To solve this problem, data processing methods such as iterative subdivision, deconvolution, and neural networks have been proposed. However, they all have some shortcomings and thus have not been widely applied. Here, we propose and experimentally demonstrate an OTDR deconvolution neural network based on deep convolutional neural networks. A simplified OTDR model is built to generate a large amount of training data. By optimizing the network structure and training data, an effective OTDR deconvolution is achieved. The simulation and experimental results show that the proposed neural network can achieve more accurate deconvolution than the conventional deconvolution algorithm with a higher signal-to-noise ratio.

eess.SP↗

arXiv2022

Thermal Modelling and Controller Design of an Alkaline Electrolysis System under Dynamic Operating Conditions

Thermal management is vital for the efficient and safe operation of alkaline electrolysis systems. Traditional alkaline electrolysis systems use simple proportional-integral-differentiation (PID) controllers to maintain the stack temperature near the rated value. However, in renewable-to-hydrogen scenarios, the stack temperature is disturbed by load fluctuations, and the temperature overshoot phenomenon occurs which can exceed the upper limit and harm the stack. This paper focuses on the thermal modelling and controller design of an alkaline electrolysis system under dynamic operating conditions. A control-oriented thermal model is established in the form of a third-order time-delay process, which is used for simulation and controller design. Based on this model, we propose two novel controllers to reduce temperature overshoot: one is a current feed-forward PID controller (PID-I), the other is a model predictive controller (MPC). Their performances are tested on a lab-scale system and the experimental results are satisfying: the temperature overshoot is reduced by 2.2 degree with the PID-I controller, and no obvious overshoot is observed with the MPC controller. Furthermore, the thermal dynamic performance of an MW-scale alkaline electrolysis system is analyzed by simulation, which shows that the temperature overshoot phenomenon is more general in large systems. The proposed method allows for higher temperature set points which can improve system efficiency by 1%.

eess.SY↗

arXiv2021

Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation

3D human pose and shape recovery from a monocular RGB image is a challenging task. Existing learning based methods highly depend on weak supervision signals, e.g. 2D and 3D joint location, due to the lack of in-the-wild paired 3D supervision. However, considering the 2D-to-3D ambiguities existed in these weak supervision labels, the network is easy to get stuck in local optima when trained with such labels. In this paper, we reduce the ambituity by optimizing multiple initializations. Specifically, we propose a three-stage framework named Multi-Initialization Optimization Network (MION). In the first stage, we strategically select different coarse 3D reconstruction candidates which are compatible with the 2D keypoints of input sample. Each coarse reconstruction can be regarded as an initialization leads to one optimization branch. In the second stage, we design a mesh refinement transformer (MRT) to respectively refine each coarse reconstruction result via a self-attention mechanism. Finally, a Consistency Estimation Network (CEN) is proposed to find the best result from mutiple candidates by evaluating if the visual evidence in RGB image matches a given 3D reconstruction. Experiments demonstrate that our Multi-Initialization Optimization Network outperforms existing 3D mesh based methods on multiple public benchmarks.

cs.CV↗

arXiv2021

MST: Masked Self-Supervised Transformer for Visual Representation

Transformer has been widely used for self-supervised pre-training in Natural Language Processing (NLP) and achieved great success. However, it has not been fully explored in visual self-supervised learning. Meanwhile, previous methods only consider the high-level feature and learning representation from a global perspective, which may fail to transfer to the downstream dense prediction tasks focusing on local features. In this paper, we present a novel Masked Self-supervised Transformer approach named MST, which can explicitly capture the local context of an image while preserving the global semantic information. Specifically, inspired by the Masked Language Modeling (MLM) in NLP, we propose a masked token strategy based on the multi-head self-attention map, which dynamically masks some tokens of local patches without damaging the crucial structure for self-supervised learning. More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks. The experiments on multiple datasets demonstrate the effectiveness and generality of the proposed method. For instance, MST achieves Top-1 accuracy of 76.9% with DeiT-S only using 300-epoch pre-training by linear evaluation, which outperforms supervised methods with the same epoch by 0.4% and its comparable variant DINO by 1.0\%. For dense prediction tasks, MST also achieves 42.7% mAP on MS COCO object detection and 74.04% mIoU on Cityscapes segmentation only with 100-epoch pre-training.

cs.CV↗

arXiv2021

Enabling variable high spatial resolution retrieval from a long pulse BOTDA sensor

In the field of Internet of Things, there is an urgent need for sensors with large-scale sensing capability for scenarios such as intelligent monitoring of production lines and urban infrastructure. Brillouin optical time domain analysis (BOTDA) sensors, which can monitor thousands of continuous points simultaneously, show great advantages in these applications. We propose a convolutional neural network (CNN) to process the data of conventional Brillouin optical time domain analysis (BOTDA) sensors, which achieves unprecedented performance improvement that allows to directly retrieve higher spatial resolution (SR) from the sensing system that use long pump pulses. By using the simulated Brillouin gain spectrums (BGSs) as the CNN input and the corresponding high SR BFS as the output target, the trained CNN is able to obtain a SR higher than the theoretical value determined by the pump pulse width. In the experiment, the CNN accurately retrieves 0.5-m hotspots from the measured BGS with pump pulses from 20 to 50 ns, and the acquired BFS is in great agreement with 45/40 ns differential pulse-width pair (DPP) measurement results. Compared with the DPP technique, the proposed CNN demonstrates a 2-fold improvement in BFS uncertainty with only half the measurement time. In addition, by changing the training datasets, the proposed CNN can obtain tunable high SR retrieval based on conventional BOTDA sensors that use long pulses without any requirement of hardware modifications. The proposed data post-processing approach paves the way to enable novel high spatial resolution BOTDA sensors, which brings substantial improvement over the state-of-the-art techniques in terms of system complexity, measurement time and reliability, etc.

eess.SP↗

arXiv2021

Identifying super-spreaders in information-epidemic coevolving dynamics on multiplex networks

Identifying super-spreaders in epidemics is important to suppress the spreading of disease especially when the medical resource is limited.In the modern society, the information on epidemics transmits swiftly through various communication channels which contributes much to the suppression of epidemics. Here we study on the identification of super-spreaders in the information-disease coupled spreading dynamics. Firstly, we find that the centralities in physical contact layer are no longer effective to identify super-spreaders in epidemics, which is due to the suppression effects from the information spreading. Then by considering the structural and dynamical couplings between the communication layer and physical contact layer, we propose a centrality measure called coupling-sensitive centrality to identify super-spreaders in disease spreading. Simulation results on synthesized and real-world multiplex networks show that the proposed measure is not only much more accurate than centralities on the single network, but also outperforms two typical multilayer centralities in identifying super-spreaders. These findings imply that considering the structural and dynamical couplings between layers is very necessary in identifying the key roles in the coupled multilayer systems.

physics.soc-ph↗

arXiv2021

A rigorous and efficient approach to finding and quantifying symmetries in complex networks

Symmetries are fundamental to dynamical processes in complex networks such as cluster synchronization, which have attracted a great deal of current research. Finding symmetric nodes in large complex networks, however, has relied on automorphism groups in algebraic group theory, which are solvable in quasipolynomial time. We articulate a conceptually appealing and computationally extremely efficient approach to finding and characterizing all symmetric nodes by introducing a structural position vector (SPV) for each and every node in the network. We prove mathematically that nodes with the identical SPV are symmetrical to each other. Utilizing six representative complex networks from the real world, we demonstrate that all symmetric nodes can be found in linear time, and the SPVs can not only characterize the similarity of nodes but also quantify the nodal influences in spreading dynamics on the network. Our SPV-based framework, in additional to being rigorously justified, provides a physically intuitive way to uncover, understand and exploit symmetric structures in complex networks.

physics.soc-ph↗

arXiv2021

DPT: Deformable Patch-based Transformer for Visual Recognition

Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this problem, we propose a new Deformable Patch (DePatch) module which learns to adaptively split the images into patches with different positions and scales in a data-driven way rather than using predefined fixed patches. In this way, our method can well preserve the semantics in patches. The DePatch module can work as a plug-and-play module, which can easily be incorporated into different transformers to achieve an end-to-end training. We term this DePatch-embedded transformer as Deformable Patch-based Transformer (DPT) and conduct extensive evaluations of DPT on image classification and object detection. Results show DPT can achieve 81.9% top-1 accuracy on ImageNet classification, and 43.7% box mAP with RetinaNet, 44.3% with Mask R-CNN on MSCOCO object detection. Code has been made available at: https://github.com/CASIA-IVA-Lab/DPT .

cs.CV↗

arXiv2021

The relative importance of structure and dynamics on node influence in reversible spreading processes

The reversible spreading processes with repeated infection widely exist in nature and human society, such as gonorrhea propagation and meme spreading. Identifying influential spreaders is an important issue in the reversible spreading dynamics on complex networks, which has been given much attention. Except for structural centrality, the nodes' dynamical states play a significant role in their spreading influence in the reversible spreading processes. By integrating the number of outgoing edges and infection risks of node's neighbors into structural centrality, a new measure for identifying influential spreaders is articulated which considers the relative importance of structure and dynamics on node influence. The number of outgoing edges and infection risks of neighbors represent the positive effect of the local structural characteristic and the negative effect of the dynamical states of nodes in identifying influential spreaders, respectively. We find that an appropriate combination of these two characteristics can greatly improve the accuracy of the proposed measure in identifying the most influential spreaders. Notably, compared with the positive effect of the local structural characteristic, slightly weakening the negative effect of dynamical states of nodes can make the proposed measure play the best performance. Quantitatively understanding the relative importance of structure and dynamics on node influence provides a significant insight into identifying influential nodes in the reversible spreading processes.

physics.soc-ph↗

arXiv2021

Adaptive Class Suppression Loss for Long-Tail Object Detection

To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies. These methods bring the following two problems. One is the training inconsistency between adjacent categories of similar sizes, and the other is that the learned model is lack of discrimination for tail categories which are semantically similar to some of the head categories. In this paper, we devise a novel Adaptive Class Suppression Loss (ACSL) to effectively tackle the above problems and improve the detection performance of tail categories. Specifically, we introduce a statistic-free perspective to analyze the long-tail distribution, breaking the limitation of manual grouping. According to this perspective, our ACSL adjusts the suppression gradients for each sample of each class adaptively, ensuring the training consistency and boosting the discrimination for rare categories. Extensive experiments on long-tail datasets LVIS and Open Images show that the our ACSL achieves 5.18% and 5.2% improvements with ResNet50-FPN, and sets a new state of the art. Code and models are available at https://github.com/CASIA-IVA-Lab/ACSL.

cs.CV↗

arXiv2021

Interference fading suppression in Phi-OTDR using space-division multiplexed probes

We propose and experimentally demonstrate a novel interference fading suppression method for phase-sensitive optical time domain reflectometry (Phi-OTDR) using space-division multiplexed (SDM) pulse probes in few-mode fiber. The SDM probes consist of multiple different modes, and three spatial modes (LP01, LP11a and LP11b) are used in this work for proof of concept. Firstly, the Rayleigh backscattering light of different modes is experimentally characterized, and it turns out that the waveforms of Phi-OTDR traces of distinct modes are all different from each other. Thanks to the spatial difference of fading positions of distinct modes, multiple probes from spatially multiplexed modes can be used to suppress the interference fading in Phi-OTDR. Then, the performances of the Phi-OTDR systems using single probe and multiple probes are evaluated and compared. Specifically, statistical analysis shows that both fading probabilities over fiber length and time are reduced significantly by using multiple SDM probes, which verifies the significant performance improvement on fading suppression. The proposed novel interference fading suppression method does not require complicated frequency or phase modulation, which has the advantages of simplicity, good effectiveness and high reliability.

physics.optics↗

arXiv2021

Identify Influential Spreaders in Asymmetrically Interacting Multiplex Networks

Identifying the most influential spreaders is important to understand and control the spreading process in a network. As many real-world complex systems can be modeled as multilayer networks, the question of identifying important nodes in multilayer network has attracted much attention. Existing studies focus on the multilayer network structure, while neglecting how the structural and dynamical coupling of multiple layers influence the dynamical importance of nodes in the network. Here we investigate on this question in an information-disease coupled spreading dynamics on multiplex networks. Firstly, we explicitly reveal that three interlayer coupling factors, which are the two-layer relative spreading speed, the interlayer coupling strength and the two-layer degree correlation, significantly impact the spreading influence of a node on the contact layer. The suppression effect from the information layer makes the structural centrality on the contact layer fail to predict the spreading influence of nodes in the multiplex network. Then by mapping the coevolving spreading dynamics into percolation process and using the message-passing approach, we propose a method to calculate the size of the disease outbreaks from a single seed node, which can be used to estimate the nodes' spreading influence in the coevolving dynamics. Our work provides insights on the importance of nodes in the multiplex network and gives a feasible framework to investigate influential spreaders in the asymmetrically coevolving dynamics.

physics.soc-ph↗

arXiv2021

Asymmetrically interacting dynamics with mutual confirmation from multi-source on multiplex networks

In the early stage of epidemics, individuals' determination on adopting protective measures, which can reduce their risk of infection and suppress disease spreading, is likely to depend on multiple information sources and their mutual confirmation due to inadequate exact information. Here we introduce the inter-layer mutual confirmation mechanism into the information-disease interacting dynamics on multiplex networks. In our model, an individual increases the information transmission rate and willingness to adopt protective measures once he confirms the authenticity of news and severity of disease from neighbors status in multiple layers. By using the microscopic Markov chain approach, we analytically calculate the epidemic threshold and the awareness and infected density in the stationary state, which agree well with simulation results. We find that the increment of epidemic threshold when confirming the aware neighbors on communication layer is larger than that of the contact layer. On the contrary, the confirmation of neighbors' awareness and infection from the contact layer leads to a lower final infection density and a higher awareness density than that of the communication layer. The results imply that individuals' explicit exposure of their infection and awareness status to neighbors, especially those with real contacts, is helpful in suppressing epidemic spreading.

physics.soc-ph↗

arXiv2020

Quantitative assessment of the effects of resource optimization and ICU admission policy on COVID-19 mortalities

It is evident that increasing the intensive-care-unit (ICU) capacity and giving priority to admitting and treating younger patients will reduce the number of COVID-19 deaths, but a quantitative assessment of these measures has remained inadequate. We develop a comprehensive, non-Markovian state transition model, which is validated through accurate prediction of the daily death toll for two epicenters: Wuhan, China and Lombardy, Italy. The model enables prediction of COVID-19 deaths in various scenarios. For example, if treatment priorities had been given to younger patients, the death toll in Wuhan and Lombardy would have been reduced by 10.4\% and 6.7\%, respectively. The strategy depends on the epidemic scale and is more effective in countries with a younger population structure. Analyses of data from China, South Korea, Italy, and Spain suggest that countries with less per capita ICU medical resources should implement this strategy in the early stage of the pandemic to reduce mortalities.

physics.soc-ph↗

arXiv2020

Fast Kernelized Correlation Filters without Boundary Effect

In recent years, correlation filter based trackers (CF trackers) have attracted much attention from the vision community because of their top performance in both localization accuracy and efficiency. The society of visual tracking, however, still needs to deal with the following difficulty on CF trackers: avoiding or eliminating the boundary effect completely, in the meantime, exploiting non-linear kernels and running efficiently. In this paper, we propose a fast kernelized correlation filter without boundary effect (nBEKCF) to solve this problem. To avoid the boundary effect thoroughly, a set of \emph{real} and \emph{dense} patches is sampled through the traditional sliding window and used as the training samples to train nBEKCF to fit a Gaussian response map. Non-linear kernels can be applied naturally in nBEKCF due to its different theoretical foundation from the existing CF trackers'. To achieve the fast training and detection, a set of cyclic bases is introduced to construct the filter. Two algorithms, ACSII and CCIM, are developed to significantly accelerate the calculation of kernel correlation matrices. ACSII and CCIM fully exploit the density of training samples and cyclic structure of bases, and totally run in space domain. The efficiency of CCIM exceeds that of the FFT counterpart remarkably in our task. Extensive experiments on six public datasets, OTB-2013, OTB-2015, NfS, VOT2018, GOT10k, and TrackingNet, show that compared to the CF trackers designed to relax the boundary effect, BACF and SRDCF, our nBEKCF achieves higher localization accuracy without tricks, in the meanwhile, runs at higher FPS.

cs.CV↗