Search arXiv⌕ Search

arXiv subjects

Li Chen

Publications and source records attributed to Li Chen.

At least 487 records · Page 27Linked to original sources
arXiv2021

Cascade Image Matting with Deformable Graph Refinement

Image matting refers to the estimation of the opacity of foreground objects. It requires correct contours and fine details of foreground objects for the matting results. To better accomplish human image matting tasks, we propose the Cascade Image Matting Network with Deformable Graph Refinement, which can automatically predict precise alpha mattes from single human images without any additional inputs. We adopt a network cascade architecture to perform matting from low-to-high resolution, which corresponds to coarse-to-fine optimization. We also introduce the Deformable Graph Refinement (DGR) module based on graph neural networks (GNNs) to overcome the limitations of convolutional neural networks (CNNs). The DGR module can effectively capture long-range relations and obtain more global and local information to help produce finer alpha mattes. We also reduce the computation complexity of the DGR module by dynamically predicting the neighbors and apply DGR module to higher--resolution features. Experimental results demonstrate the ability of our CasDGR to achieve state-of-the-art performance on synthetic datasets and produce good results on real human images.

cs.CV↗
arXiv2021

Improving Robustness for Pose Estimation via Stable Heatmap Regression

Deep learning methods have achieved excellent performance in pose estimation, but the lack of robustness causes the keypoints to change drastically between similar images. In view of this problem, a stable heatmap regression method is proposed to alleviate network vulnerability to small perturbations. We utilize the correlation between different rows and columns in a heatmap to alleviate the multi-peaks problem, and design a highly differentiated heatmap regression to make a keypoint discriminative from surrounding points. A maximum stability training loss is used to simplify the optimization difficulty when minimizing the prediction gap of two similar images. The proposed method achieves a significant advance in robustness over state-of-the-art approaches on two benchmark datasets and maintains high performance.

cs.CV↗
arXiv2021

Hermite Polynomial-based Valuation of American Options with General Jump-Diffusion Processes

We present a new approximation scheme for the price and exercise policy of American options. The scheme is based on Hermite polynomial expansions of the transition density of the underlying asset dynamics and the early exercise premium representation of the American option price. The advantages of the proposed approach are threefold. First, our approach does not require the transition density and characteristic functions of the underlying asset dynamics to be attainable in closed form. Second, our approach is fast and accurate, while the prices and exercise policy can be jointly produced. Third, our approach has a wide range of applications. We show that the proposed approximations of the price and optimal exercise boundary converge to the true ones. We also provide a numerical method based on a step function to implement our proposed approach. Applications to nonlinear mean-reverting models, double mean-reverting models, Merton's and Kou's jump-diffusion models are presented and discussed.

q-fin.CP↗
arXiv2021

Simulating Unknown Target Models for Query-Efficient Black-box Attacks

Many adversarial attacks have been proposed to investigate the security issues of deep neural networks. In the black-box setting, current model stealing attacks train a substitute model to counterfeit the functionality of the target model. However, the training requires querying the target model. Consequently, the query complexity remains high, and such attacks can be defended easily. This study aims to train a generalized substitute model called "Simulator", which can mimic the functionality of any unknown target model. To this end, we build the training data with the form of multiple tasks by collecting query sequences generated during the attacks of various existing networks. The learning process uses a mean square error-based knowledge-distillation loss in the meta-learning to minimize the difference between the Simulator and the sampled networks. The meta-gradients of this loss are then computed and accumulated from multiple tasks to update the Simulator and subsequently improve generalization. When attacking a target model that is unseen in training, the trained Simulator can accurately simulate its functionality using its limited feedback. As a result, a large fraction of queries can be transferred to the Simulator, thereby reducing query complexity. Results of the comprehensive experiments conducted using the CIFAR-10, CIFAR-100, and TinyImageNet datasets demonstrate that the proposed approach reduces query complexity by several orders of magnitude compared to the baseline method. The implementation source code is released at https://github.com/machanic/SimulatorAttack.

cs.CV↗
arXiv2021

On the Robustness of Monte Carlo Dropout Trained with Noisy Labels

The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic uncertainty techniques are robust when trained with noisy labels compared with neural networks without uncertainty estimation. They obtain prolonged memorization effect and better generalization performance under the adversarial setting of noisy labels. Due to its superior performance amongst other selected epistemic uncertainty methods under noisy labels, we focus on Monte Carlo Dropout (MCDropout) and investigate why it is robust when trained with noisy labels. Through empirical studies on datasets MNIST, CIFAR-10, Animal-10n, we deep dive into three aspects of MCDropout under noisy label setting: 1. efficacy: understanding the learning behavior and test accuracy of MCDropout when training set contains artificially generated or naturally embedded label noise; 2. representation volatility: studying the responsiveness of neurons by examining the mean and standard deviation on each neuron's activation; 3. network sparsity: investigating the network support of MCDropout in comparison with deterministic neural networks. Our findings suggest that MCDropout further sparsifies and regularizes the deterministic neural networks and thus provides higher robustness against noisy labels.

cs.LG↗
arXiv2021

Blind Diagnosis for Millimeter-wave Large-scale Antenna Systems

Millimeter-wave (mmWave) communication systems rely on large-scale antenna arrays to combat large path-loss at mmWave band. Due to hardware characteristics and deployment environments, mmWave large-scale antenna systems are vulnerable to antenna element blockages and failures, which necessitate diagnostic techniques to locate faulty antenna elements for calibration purposes. Current diagnostic techniques require full or partial knowledge of channel state information (CSI), which can be challenging to acquire in the presence of antenna failures. In this letter, we propose a blind diagnostic technique to identify faulty antenna elements in mmWave large-scale antenna systems, which does not require any CSI knowledge. By jointly exploiting the sparsity of mmWave channel and failure pattern, we first formulate the diagnosis problem as a joint sparse recovery problem. Then, the atomic norm is introduced to induce the sparsity of mmWave channel over continuous Fourier dictionary. An efficient algorithm based on alternating direction method of multipliers (ADMM) is proposed to solve the formulated problem. Finally, the performance of the proposed technique is evaluated through numerical simulations.

eess.SY↗
arXiv2021

Insight-HXMT observations of jet-like corona in a black hole X-ray binary MAXI J1820+070

A black hole X-ray binary produces hard X-ray radiation from its corona and disk when the accreting matter heats up. During an outburst, the disk and corona co-evolves with each other. However, such an evolution is still unclear in both its geometry and dynamics. Here we report the unusual decrease of the reflection fraction in MAXI J1820+070, which is the ratio of the coronal intensity illuminating the disk to the coronal intensity reaching the observer, as the corona is observed to contrast during the decay phase. We postulate a jet-like corona model, in which the corona can be understood as a standing shock where the material flowing through. In this dynamical scenario, the decrease of the reflection fraction is a signature of the corona's bulk velocity. Our findings suggest that as the corona is observed to get closer to the black hole, the coronal material might be outflowing faster.

astro-ph.HE↗
arXiv2021

Speech enhancement with weakly labelled data from AudioSet

Speech enhancement is a task to improve the intelligibility and perceptual quality of degraded speech signal. Recently, neural networks based methods have been applied to speech enhancement. However, many neural network based methods require noisy and clean speech pairs for training. We propose a speech enhancement framework that can be trained with large-scale weakly labelled AudioSet dataset. Weakly labelled data only contain audio tags of audio clips, but not the onset or offset times of speech. We first apply pretrained audio neural networks (PANNs) to detect anchor segments that contain speech or sound events in audio clips. Then, we randomly mix two detected anchor segments containing speech and sound events as a mixture, and build a conditional source separation network using PANNs predictions as soft conditions for speech enhancement. In inference, we input a noisy speech signal with the one-hot encoding of "Speech" as a condition to the trained system to predict enhanced speech. Our system achieves a PESQ of 2.28 and an SSNR of 8.75 dB on the VoiceBank-DEMAND dataset, outperforming the previous SEGAN system of 2.16 and 7.73 dB respectively.

cs.SD↗
arXiv2021

Social hierarchy promotes the cooperation prevalence

Social hierarchy is important that can not be ignored in human socioeconomic activities and in the animal world. Here we incorporate this factor into the evolutionary game to see what impact it could have on the cooperation outcome. The probabilistic strategy adoption between two players is then not only determined by their payoffs, but also by their hierarchy difference -- players in the high rank are more likely to reproduce their strategies than the peers in the low rank. Through simulating the evolution of Prisoners' dilemma game with three hierarchical distributions, we find that the levels of cooperation are enhanced in all cases, and the enhancement is optimal in the uniform case. The enhancement is due to the fact that the presence of hierarchy facilitates the formation of cooperation clusters with high-rank players acting as the nucleation cores. This mechanism remains valid on Barabási-Albert scale-free networks, in particular the cooperation enhancement is maximal when the hubs are of higher social ranks. We also study a two-hierarchy model, where similar cooperation promotion is revealed and some theoretical analyses are provided. Our finding may partially explain why the social hierarchy is so ubiquitous on this planet.

physics.soc-ph↗
arXiv2021

BU-Trace: A Permissionless Mobile System for Privacy-Preserving Intelligent Contact Tracing

The coronavirus disease 2019 (COVID-19) pandemic has caused an unprecedented health crisis for the global. Digital contact tracing, as a transmission intervention measure, has shown its effectiveness on pandemic control. Despite intensive research on digital contact tracing, existing solutions can hardly meet users' requirements on privacy and convenience. In this paper, we propose BU-Trace, a novel permissionless mobile system for privacy-preserving intelligent contact tracing based on QR code and NFC technologies. First, a user study is conducted to investigate and quantify the user acceptance of a mobile contact tracing system. Second, a decentralized system is proposed to enable contact tracing while protecting user privacy. Third, an intelligent behavior detection algorithm is designed to ease the use of our system. We implement BU-Trace and conduct extensive experiments in several real-world scenarios. The experimental results show that BU-Trace achieves a privacy-preserving and intelligent mobile system for contact tracing without requesting location or other privacy-related permissions.

cs.SI↗
arXiv2020

Smooth solutions to the Gauss image problem

In this paper we study the the Gauss image problem, which is a generalization of the Aleksandrov problem in convex geometry. By considering a geometric flow involving Gauss curvature and functions of normal vectors and radial vectors, we obtain the existence of smooth solutions to this problem.

math.AP↗
arXiv2020

A spectral-based framework for hypothesis testing in populations of networks

In this paper, we propose a new spectral-based approach to hypothesis testing for populations of networks. The primary goal is to develop a test to determine whether two given samples of networks come from the same random model or distribution. Our test statistic is based on the trace of the third order for a centered and scaled adjacency matrix, which we prove converges to the standard normal distribution as the number of nodes tends to infinity. The asymptotic power guarantee of the test is also provided. The proper interplay between the number of networks and the number of nodes for each network is explored in characterizing the theoretical properties of the proposed testing statistics. Our tests are applicable to both binary and weighted networks, operate under a very general framework where the networks are allowed to be large and sparse, and can be extended to multiple-sample testing. We provide an extensive simulation study to demonstrate the superior performance of our test over existing methods and apply our test to three real datasets.

stat.ME↗
arXiv2020

Robust Deep Learning with Active Noise Cancellation for Spatial Computing

This paper proposes CANC, a Co-teaching Active Noise Cancellation method, applied in spatial computing to address deep learning trained with extreme noisy labels. Deep learning algorithms have been successful in spatial computing for land or building footprint recognition. However a lot of noise exists in ground truth labels due to how labels are collected in spatial computing and satellite imagery. Existing methods to deal with extreme label noise conduct clean sample selection and do not utilize the remaining samples. Such techniques can be wasteful due to the cost of data retrieval. Our proposed CANC algorithm not only conserves high-cost training samples but also provides active label correction to better improve robust deep learning with extreme noisy labels. We demonstrate the effectiveness of CANC for building footprint recognition for spatial computing.

cs.LG↗
arXiv2020

The Bayesian Committee Approach for Computational Physics Problems

In this work, we propose a method for efficient learning of a multi-dimensional function. This method combines the Bayesian neural networks and the query-by-committee method. A committee made of deep Bayesian neural networks not only can provide uncertainty of the prediction but also can provide the discrepancy between committee members. Both the uncertainty and the discrepancy are large in the regions where the target function varies rapidly, and therefore, both quantities can be used to guide sampling data to such regions. In this way, we can learn a function accurately with the number of queried data points much less than uniform sampling. Here we test our method with two examples. One example is to find a rare phase in a phase diagram, which is separated from other phases by a second-order phase transition. In this example, the target function is the susceptibility function, and since the divergence of the susceptibility function locates the phase diagram, the task of searching such a phase perfectly matches the advantage of our method. Another example is to learn the distribution function for Monte Carlo integration of a high-dimensional function. In both examples, we show that our method performs significantly efficiently than uniform sampling. Our method can find broad applications in computational scientific problems.

physics.comp-ph↗
arXiv2020

DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images

Change detection is a basic task of remote sensing image processing. The research objective is to identity the change information of interest and filter out the irrelevant change information as interference factors. Recently, the rise of deep learning has provided new tools for change detection, which have yielded impressive results. However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudo-change information. To overcome the lack of resistance of current methods to pseudo-changes, in this paper, we propose a new method, namely, dual attentive fully convolutional Siamese networks (DASNet) for change detection in high-resolution images. Through the dual-attention mechanism, long-range dependencies are captured to obtain more discriminant feature representations to enhance the recognition performance of the model. Moreover, the imbalanced sample is a serious problem in change detection, i.e. unchanged samples are much more than changed samples, which is one of the main reasons resulting in pseudo-changes. We put forward the weighted double margin contrastive loss to address this problem by punishing the attention to unchanged feature pairs and increase attention to changed feature pairs. The experimental results of our method on the change detection dataset (CDD) and the building change detection dataset (BCDD) demonstrate that compared with other baseline methods, the proposed method realizes maximum improvements of 2.1\% and 3.6\%, respectively, in the F1 score. Our Pytorch implementation is available at https://github.com/lehaifeng/DASNet.

cs.CV↗
arXiv2020

Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins

Computational fluid dynamics (CFD) model has been widely used for prototyping data centers. Evolving it to high-fidelity {\em digital twin} is desirable for the management and operations of large-scale data centers. Manually calibrating CFD model parameters to achieve twin-class fidelity by specially trained domain expert is tedious and labor-intensive. To reduce manual efforts, existing automatic calibration approaches developed for various computational models apply heuristics to search model configurations within an empirically defined parameter bound. However, in the context of CFD, each search step requires long-lasting CFD model's iterated solving, rendering these approaches impractical with increased model complexity. This paper presents Kalibre, a knowledge-based neural surrogate approach that performs CFD model calibration by iterating four key steps of i) training a neural surrogate model based on CFD-generated data, ii) finding the optimal parameters at the moment through neural surrogate retraining based on sensor-measured data, iii) configuring the found parameters back to the CFD model, and iv) validating the CFD model using sensor-measured data as the ground truth. Thus, the parameter search is offloaded to the neural surrogate which is ultra-faster than CFD model's iterated solving. To speed up the convergence of Kalibre, we integrate prior knowledge of the twinned data center's thermophysics into the neural surrogate design to improve its learning efficiency. With about five hours computation on a 32-core processor, Kalibre achieves mean absolute errors (MAEs) of $0.81^o$C and $0.75^o$C in calibrating two CFD models for two production data halls hosting thousands of servers each while requires fewer CFD solving processes than existing baseline approaches.

eess.SY↗