arXiv subjects

Jie Chen

Publications and source records attributed to Jie Chen.

At least 523 records · Page 29Linked to original sources

arXiv2021

Bias, Fairness, and Accountability with AI and ML Algorithms

The advent of AI and ML algorithms has led to opportunities as well as challenges. In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms. We describe the types and sources of data bias, and discuss the nature of algorithmic unfairness. This is followed by a review of fairness metrics in the literature, discussion of their limitations, and a description of de-biasing (or mitigation) techniques in the model life cycle.

stat.ML↗

arXiv2021

Unsupervised domain adaptation via double classifiers based on high confidence pseudo label

Unsupervised domain adaptation (UDA) aims to solve the problem of knowledge transfer from labeled source domain to unlabeled target domain. Recently, many domain adaptation (DA) methods use centroid to align the local distribution of different domains, that is, to align different classes. This improves the effect of domain adaptation, but domain differences exist not only between classes, but also between samples. This work rethinks what is the alignment between different domains, and studies how to achieve the real alignment between different domains. Previous DA methods only considered one distribution feature of aligned samples, such as full distribution or local distribution. In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution. Therefore, this study propose a double classifier method based on high confidence label (DCP). By aligning the centroid and the distribution between centroid and sample of different classifiers, the meso and micro distribution alignment of different domains is realized. In addition, in order to reduce the chain error caused by error marking, This study propose a high confidence marking method to reduce the marking error. To verify its versatility, this study evaluates DCP on digital recognition and target recognition data sets. The results show that our method achieves state-of-the-art results on most of the current domain adaptation benchmark datasets.

cs.CV↗

arXiv2021

Geometrical Characterization of Sensor Placement for Cone-Invariant and Multi-Agent Systems against Undetectable Zero-Dynamics Attacks

Undetectable attacks are an important class of malicious attacks threatening the security of cyber-physical systems, which can modify a system's state but leave the system output measurements unaffected, and hence cannot be detected from the output. This paper studies undetectable attacks on cone-invariant systems and multi-agent systems. We first provide a general characterization of zero-dynamics attacks, which characterizes fully undetectable attacks targeting the non-minimum phase zeros of a system. This geometrical characterization makes it possible to develop a defense strategy seeking to place a minimal number of sensors to detect and counter the zero-dynamics attacks on the system's actuators. The detect and defense scheme amounts to computing a set containing potentially vulnerable actuator locations and nodes, and a defense union for feasible placement of sensors based on the geometrical properties of the cones under consideration.

eess.SY↗

arXiv2021

Planar topological Hall effect in a hexagonal ferromagnetic Fe5Sn3 single crystal

The planar topological Hall effect (PTHE), appeared when the magnetic field tended to be along the current, is believed to result from the real-space Berry curvature of the spin spiral structure and has been experimentally observed in skyrmion-hosting materials. In this paper, we report an experimental observation of the PTHE in a hexagonal ferromagnetic Fe5Sn3 single crystal. With a current along the c axis of Fe5Sn3, the transverse resistivity curves exhibited obvious peaks near the saturation field as the magnetic field rotated to the current and appeared more obvious with increasing temperature, which was related to the noncoplanar spin structure in Fe5Sn3. This spin structure induced nonzero scalar spin chirality, which acted as fictitious magnetic fields to conduction electrons and contributed the additional transverse signal. These findings deepen the understanding of the interaction between conduction electrons and complex magnetic structures and are instructive for the design of next-generation spintronic devices.

cond-mat.mtrl-sci↗

arXiv2021

RR-Net: Injecting Interactive Semantics in Human-Object Interaction Detection

Human-Object Interaction (HOI) detection devotes to learn how humans interact with surrounding objects. Latest end-to-end HOI detectors are short of relation reasoning, which leads to inability to learn HOI-specific interactive semantics for predictions. In this paper, we therefore propose novel relation reasoning for HOI detection. We first present a progressive Relation-aware Frame, which brings a new structure and parameter sharing pattern for interaction inference. Upon the frame, an Interaction Intensifier Module and a Correlation Parsing Module are carefully designed, where: a) interactive semantics from humans can be exploited and passed to objects to intensify interactions, b) interactive correlations among humans, objects and interactions are integrated to promote predictions. Based on modules above, we construct an end-to-end trainable framework named Relation Reasoning Network (abbr. RR-Net). Extensive experiments show that our proposed RR-Net sets a new state-of-the-art on both V-COCO and HICO-DET benchmarks and improves the baseline about 5.5% and 9.8% relatively, validating that this first effort in exploring relation reasoning and integrating interactive semantics has brought obvious improvement for end-to-end HOI detection.

cs.CV↗

arXiv2021

Distributed Linear Equations over Random Networks

Distributed linear algebraic equation over networks, where nodes hold a part of problem data and cooperatively solve the equation via node-to-node communications, is a basic distributed computation task receiving an increasing research attention. Communications over a network have a stochastic nature, with both temporal and spatial dependence due to link failures, packet dropouts or node recreation, etc. In this paper, we study the convergence and convergence rate of distributed linear equation protocols over a $\ast$-mixing random network, where the temporal and spatial dependencies between the node-to-node communications are allowed. When the network linear equation admits exact solutions, we prove the mean-squared exponential convergence rate of the distributed projection consensus algorithm, while the lower and upper bound estimations of the convergence rate are also given for independent and identically distributed (i.i.d.) random graphs. Motivated by the randomized Kaczmarz algorithm, we also propose a distributed randomized projection consensus algorithm, where each node randomly selects one row of local linear equations for projection per iteration, and establish an exponential convergence rate. When the network linear equation admits no exact solution, we prove that a distributed gradient-descent-like algorithm with diminishing step-sizes can drive all nodes' states to a least-squares solution at a sublinear rate. These results collectively illustrate that distributed computations may overcome communication correlations if the prototype algorithms enjoy certain contractive properties or are designed with suitable parameters.

math.OC↗

arXiv2021

Underwater Target Recognition based on Multi-Decision LOFAR Spectrum Enhancement: A Deep Learning Approach

The Low frequency analysis and recording (LOFAR) spectrum is one of the key features of the under water target, which can be used for underwater target recognition. However, the underwater environment noise is complicated and the signal-to-noise ratio of the underwater target is rather low, which introduces the breakpoints to the LOFAR spectrum and thus hinders the underwater target recognition. To overcome this issue and to further improve the recognition performance, we adopt a deep learning approach for underwater target recognition and propose a LOFAR spectrum enhancement (LSE)-based underwater target recognition scheme, which consists of preprocessing, offline training, and online testing. In preprocessing, a LOFAR spectrum enhancement based on multi-step decision algorithm is specifically designed to recover the breakpoints in LOFAR spectrum. In offline training, we then adopt the enhanced LOFAR spectrum as the input of convolutional neural network (CNN) and develop a LOFAR-based CNN (LOFAR-CNN) for online recognition. Taking advantage of the powerful capability of CNN in feature extraction, the proposed LOFAR-CNN can further improve the recognition accuracy. Finally, extensive simulation results demonstrate that the LOFAR-CNN network can achieve a recognition accuracy of $95.22\%$, which outperforms the state-of-the-art methods.

eess.SP↗

arXiv2021

Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation

Hyperspectral image (HSI) super-resolution is commonly used to overcome the hardware limitations of existing hyperspectral imaging systems on spatial resolution. It fuses a low-resolution (LR) HSI and a high-resolution (HR) conventional image of the same scene to obtain an HR HSI. In this work, we propose a method that integrates a physical model and deep prior information. Specifically, a novel, yet effective two-stream fusion network is designed to serve as a {regularizer} for the fusion problem. This fusion problem is formulated as an optimization problem whose solution can be obtained by solving a Sylvester equation. Furthermore, the regularization parameter is simultaneously estimated to automatically adjust contribution of the physical model and {the} learned prior to reconstruct the final HR HSI. Experimental results on {both simulated and real data} demonstrate the superiority of the proposed method over other state-of-the-art methods on both quantitative and qualitative comparisons.

eess.IV↗

arXiv2021

A Plug-and-Play Priors Framework for Hyperspectral Unmixing

Spectral unmixing is a widely used technique in hyperspectral image processing and analysis. It aims to separate mixed pixels into the component materials and their corresponding abundances. Early solutions to spectral unmixing are performed independently on each pixel. Nowadays, investigating proper priors into the unmixing problem has been popular as it can significantly enhance the unmixing performance. However, it is non-trivial to handcraft a powerful regularizer, and complex regularizers may introduce extra difficulties in solving optimization problems in which they are involved. To address this issue, we present a plug-and-play (PnP) priors framework for hyperspectral unmixing. More specifically, we use the alternating direction method of multipliers (ADMM) to decompose the optimization problem into two iterative subproblems. One is a regular optimization problem depending on the forward model, and the other is a proximity operator related to the prior model and can be regarded as an image denoising problem. Our framework is flexible and extendable which allows a wide range of denoisers to replace prior models and avoids handcrafting regularizers. Experiments conducted on both synthetic data and real airborne data illustrate the superiority of the proposed strategy compared with other state-of-the-art hyperspectral unmixing methods.

eess.SP↗

arXiv2021

Discrete Graph Structure Learning for Forecasting Multiple Time Series

Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model. When using deep neural networks as forecasting models, we hypothesize that exploiting the pairwise information among multiple (multivariate) time series also improves their forecast. If an explicit graph structure is known, graph neural networks (GNNs) have been demonstrated as powerful tools to exploit the structure. In this work, we propose learning the structure simultaneously with the GNN if the graph is unknown. We cast the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution. The distribution is parameterized by a neural network so that discrete graphs can be sampled differentiably through reparameterization. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning, as well as a broad array of forecasting models, either deep or non-deep learning based, and graph or non-graph based.

cs.LG↗

arXiv2021

Image-based Virtual Fitting Room

Virtual fitting room is a challenging task yet useful feature for e-commerce platforms and fashion designers. Existing works can only detect very few types of fashion items. Besides they did poorly in changing the texture and style of the selected fashion items. In this project, we propose a novel approach to address this problem. We firstly used Mask R-CNN to find the regions of different fashion items, and secondly used Neural Style Transfer to change the style of the selected fashion items. The dataset we used is composed of images from PaperDoll dataset and annotations provided by eBay's ModaNet. We trained 8 models and our best model massively outperformed baseline models both quantitatively and qualitatively, with 68.72% mAP, 0.2% ASDR.

cs.CV↗

arXiv2021

Edge Adaptive Hybrid Regularization Model For Image Deblurring

The parameter selection is crucial to regularization based image restoration methods. Generally speaking, a spatially fixed parameter for regularization item in the whole image does not perform well for both edge and smooth areas. A larger parameter of regularization item reduces noise better in smooth areas but blurs edge regions, while a small parameter sharpens edge but causes residual noise. In this paper, an automated spatially adaptive regularization model, which combines the harmonic and TV models, is proposed for reconstruction of noisy and blurred images. In the proposed model, it detects the edges and then spatially adjusts the parameters of Tikhonov and TV regularization terms for each pixel according to the edge information. Accordingly, the edge information matrix will be also dynamically updated during the iterations. Computationally, the newly-established model is convex, which can be solved by the semi-proximal alternating direction method of multipliers (sPADMM) with a linear-rate convergence rate. Numerical simulation results demonstrate that the proposed model effectively reserves the image edges and eliminates the noise and blur at the same time. In comparison to state-of-the-art algorithms, it outperforms other methods in terms of PSNR, SSIM and visual quality.

eess.IV↗

arXiv2021

Distributed synchronous and asynchronous algorithms for semi-definite programming with diagonal constraints

This paper develops distributed synchronous and asynchronous algorithms for the large-scale semi-definite programming with diagonal constraints, which has wide applications in combination optimization, image processing and community detection. The information of the semi-definite programming is allocated to multiple interconnected agents such that each agent aims to find a solution by communicating to its neighbors. Based on low-rank property of solutions and the Burer-Monteiro factorization, we transform the original problem into a distributed optimization problem over unit spheres to reduce variable dimensions and ensure positive semi-definiteness without involving semi-definite projections, which are computationally expensive. For the distributed optimization problem, we propose distributed synchronous and asynchronous algorithms, both of which reduce computational burden and storage space compared with existing centralized algorithms. Specifically, the distributed synchronous algorithm almost surely escapes strict saddle points and converges to the set of optimal solutions to the optimization problem. In addition, the proposed distributed asynchronous algorithm allows communication delays and converges to the set of critical points to the optimization problem under mild conditions. By applying proposed algorithms to image segmentation applications, we illustrate the efficiency and convergence performance of the two proposed algorithms.

math.OC↗

arXiv2021

Noise Injection-based Regularization for Point Cloud Processing

Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regularization in the point cloud domain is rarely exploited, and most of the state-of-the-art works focus on data augmentation-based regularization. In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs. To be specific, we propose a series of regularization techniques, namely DropFeat, DropPoint and DropCluster, to perform noise injection on the point feature maps at the feature level, point level and cluster level, respectively. We also empirically analyze the impacts of different factors, including dropping rate, cluster size and dropping position, to obtain useful insights and general deployment guidelines, which can facilitate the adoption of our approaches across different datasets and DNN architectures. We evaluate our proposed approaches on various DNN models for different point cloud processing tasks. Experimental results show our approaches enable significant performance improvement. Notably, our DropCluster brings 1.5%, 1.3% and 0.8% higher overall accuracy for PointNet, PointNet++ and DGCNN, respectively, on ModelNet40 shape classification dataset. On ShapeNet part segmentation dataset, DropCluster brings 0.5%, 0.5% and 0.2% mean Intersection-over-union (IoU) increase for PointNet, PointNet++ and DGCNN, respectively. On S3DIS semantic segmentation dataset, DropCluster improves the mean IoU of PointNet, PointNet++ and DGCNN by 3.2%, 2.9% and 3.7%, respectively. Meanwhile, DropCluster also enables the overall accuracy increase for these three popular backbone DNNs by 2.4%, 2.2% and 1.8%, respectively.

cs.CV↗

arXiv2021

Resilient Control under Quantization and Denial-of-Service: Co-designing a Deadbeat Controller and Transmission Protocol

This paper is concerned with the problem of stabilizing continuous-time linear time-invariant systems subject to quantization and Denial-of-Service (DoS) attacks. In this context, two DoS-induced challenges emerge with the design of resilient encoding schemes, namely, the coupling between encoding strategies of different signals, and the synchronization between the encoder and decoder. To address these challenges, a novel structure that is equipped with a deadbeat controller as well as a delicate transmission protocol for the input and output channels, co-designed leveraging the controllability index, is put forward. When both input and output channels are subject to DoS attacks and quantization, the proposed structure is shown able to decouple the encoding schemes for input, output, and estimated output signals. This property is further corroborated by designing encoding schemes as well as conditions that ensure exponential stability of the closed-loop system. On the other hand, when only the output channel is subject to network phenomenon, the proposed structure can achieve exponential stabilization without acknowledgment (ACK) signals, in contrast to existing ACK-based results. Finally, a numerical example is given to demonstrate the practical merits of the proposed approach as well as the theory.

eess.SY↗

arXiv2021

Magnetic properties of the Shastry-Sutherland lattice material BaNd$_2$ZnO$_5$

We investigate the physical properties of the Shastry-Sutherland lattice material BaNd$_2$ZnO$_5$. Neutron diffraction, magnetic susceptibility, and specific heat measurements reveal antiferromagnetic order below 1.65 K. The magnetic order is found to be a 2-$\boldsymbol{Q}$ magnetic structure with the magnetic moments lying in the Shastry-Sutherland lattice planes comprising the tetragonal crystal structure of BaNd$_2$ZnO$_5$. The ordered moment for this structure is 1.9(1) $μ_B$ per Nd ion. Inelastic neutron scattering measurements reveal that the crystal field ground state doublet is well separated from the first excited state at 8 meV. The crystal field Hamiltonian is determined through simultaneous refinement of models with both the LS coupling and intermediate coupling approximations to the inelastic neutron scattering and magnetic susceptibility data. The ground state doublet indicates that the magnetic moments lie primarily in the basal plane with magnitude consistent with the size of the determined ordered moment.

cond-mat.str-el↗

arXiv2021

Linear Iterative Feature Embedding: An Ensemble Framework for Interpretable Model

A new ensemble framework for interpretable model called Linear Iterative Feature Embedding (LIFE) has been developed to achieve high prediction accuracy, easy interpretation and efficient computation simultaneously. The LIFE algorithm is able to fit a wide single-hidden-layer neural network (NN) accurately with three steps: defining the subsets of a dataset by the linear projections of neural nodes, creating the features from multiple narrow single-hidden-layer NNs trained on the different subsets of the data, combining the features with a linear model. The theoretical rationale behind LIFE is also provided by the connection to the loss ambiguity decomposition of stack ensemble methods. Both simulation and empirical experiments confirm that LIFE consistently outperforms directly trained single-hidden-layer NNs and also outperforms many other benchmark models, including multi-layers Feed Forward Neural Network (FFNN), Xgboost, and Random Forest (RF) in many experiments. As a wide single-hidden-layer NN, LIFE is intrinsically interpretable. Meanwhile, both variable importance and global main and interaction effects can be easily created and visualized. In addition, the parallel nature of the base learner building makes LIFE computationally efficient by leveraging parallel computing.

stat.ML↗

arXiv2021

Projection-based QLP Algorithm for Efficiently Computing Low-Rank Approximation of Matrices

Matrices with low numerical rank are omnipresent in many signal processing and data analysis applications. The pivoted QLP (p-QLP) algorithm constructs a highly accurate approximation to an input low-rank matrix. However, it is computationally prohibitive for large matrices. In this paper, we introduce a new algorithm termed Projection-based Partial QLP (PbP-QLP) that efficiently approximates the p-QLP with high accuracy. Fundamental in our work is the exploitation of randomization and in contrast to the p-QLP, PbP-QLP does not use the pivoting strategy. As such, PbP-QLP can harness modern computer architectures, even better than competing randomized algorithms. The efficiency and effectiveness of our proposed PbP-QLP algorithm are investigated through various classes of synthetic and real-world data matrices.

cs.LG↗