Search Results for author: Jie Chen

Found 220 papers, 73 papers with code

GUAP: Graph Universal Attack Through Adversarial Patching

no code implementations4 Jan 2023 Xiao Zang, Jie Chen, Bo Yuan

Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/or node data.

Graph Attention Node Classification

Position Embedding Needs an Independent Layer Normalization

no code implementations10 Dec 2022 Runyi Yu, Zhennan Wang, Yinhuai Wang, Kehan Li, Yian Zhao, Jian Zhang, Guoli Song, Jie Chen

By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.

Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors

1 code implementation28 Nov 2022 Xiuheng Wang, Jie Chen, Cédric Richard

Deconvolution is a widely used strategy to mitigate the blurring and noisy degradation of hyperspectral images~(HSI) generated by the acquisition devices.

Denoising Image Deconvolution

Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild

no code implementations25 Nov 2022 Jucai Zhai, Pengcheng Zeng, Chihao Ma, Yong Zhao, Jie Chen

The proposed method consists of a learnable blur kernel to estimate the defocus map, which is an unsupervised method, and a single-image defocus deblurring generative adversarial network (DefocusGAN) for the first time.

Deblurring Image Deblurring +1

Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation

no code implementations22 Nov 2022 Zesen Cheng, Pengchong Qiao, Kehan Li, Siheng Li, Pengxu Wei, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen

Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted.

Optical Character Recognition Weakly supervised Semantic Segmentation +1

Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations

1 code implementation21 Nov 2022 Peng Jin, Jinfa Huang, Fenglin Liu, Xian Wu, Shen Ge, Guoli Song, David A. Clifton, Jie Chen

Most video-and-language representation learning approaches employ contrastive learning, e. g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs.

 Ranked #1 on Video Retrieval on LSMDC (text-to-video Mean Rank metric)

Contrastive Learning Representation Learning +5

Dual Complementary Dynamic Convolution for Image Recognition

no code implementations11 Nov 2022 Longbin Yan, Yunxiao Qin, Shumin Liu, Jie Chen

As a powerful engine, vanilla convolution has promoted huge breakthroughs in various computer tasks.

Image Classification object-detection +2

Robust Manifold Nonnegative Tucker Factorization for Tensor Data Representation

no code implementations8 Nov 2022 Jianyu Wang, Linruize Tang, Jie Chen, Jingdong Chen

Nonnegative Tucker Factorization (NTF) minimizes the euclidean distance or Kullback-Leibler divergence between the original data and its low-rank approximation which often suffers from grossly corruptions or outliers and the neglect of manifold structures of data.

A Unified Pyramid Recurrent Network for Video Frame Interpolation

no code implementations7 Nov 2022 Xin Jin, Longhai Wu, Jie Chen, Youxin Chen, Jayoon Koo, Cheul-hee Hahm

Flow-guide synthesis provides a common framework for frame interpolation, where optical flow is typically estimated by a pyramid network, and then leveraged to guide a synthesis network to generate intermediate frames between input frames.

Optical Flow Estimation Video Frame Interpolation

SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP

1 code implementation18 Oct 2022 Jie Chen, Shouzhen Chen, Mingyuan Bai, Junbin Gao, Junping Zhang, Jian Pu

Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information.

Knowledge Distillation Node Classification

Fuzzy Positive Learning for Semi-supervised Semantic Segmentation

no code implementations16 Oct 2022 Pengchong Qiao, Zhidan Wei, Yu Wang, Zhennan Wang, Guoli Song, Fan Xu, Xiangyang Ji, Chang Liu, Jie Chen

Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations.

Semi-Supervised Semantic Segmentation

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

no code implementations12 Oct 2022 Kehan Li, Zhennan Wang, Zesen Cheng, Runyi Yu, Yian Zhao, Guoli Song, Chang Liu, Li Yuan, Jie Chen

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e. g., unsupervised semantic segmentation (USS).

Image Segmentation Unsupervised Semantic Segmentation

Flexible Alignment Super-Resolution Network for Multi-Contrast MRI

1 code implementation7 Oct 2022 Yiming Liu, Mengxi Zhang, Weiqin Zhang, Bo Jiang, Bo Hou, Dan Liu, Jie Chen, Heqing Lian

To tackle this problem, we propose the Flexible Alignment Super-Resolution Network (FASR-Net) for multi-contrast MRI Super-Resolution.

Super-Resolution

Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering

no code implementations21 Sep 2022 Hao Li, Jinfa Huang, Peng Jin, Guoli Song, Qi Wu, Jie Chen

Under this setting, these 2D spatial reasoning approaches cannot distinguish the fine-grain spatial relations between visual objects and scene texts on the same image plane, thereby impairing the interpretability and performance of TextVQA models.

Image Captioning Optical Character Recognition +2

Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability

1 code implementation24 Aug 2022 Xiuheng Wang, Ricardo Augusto Borsoi, Cédric Richard, Jie Chen

The fusion problem is stated as an optimization problem in the maximum a posteriori framework.

Data-Driven Control of Distributed Event-Triggered Network Systems

no code implementations22 Aug 2022 Xin Wang, Jian Sun, Gang Wang, Frank Allgöwer, Jie Chen

The present paper deals with data-driven event-triggered control of a class of unknown discrete-time interconnected systems (a. k. a.

Pathway to Future Symbiotic Creativity

no code implementations18 Aug 2022 Yike Guo, Qifeng Liu, Jie Chen, Wei Xue, Henrik Jensen, Fernando Rosas, Jeffrey Shaw, Xing Wu, Jiji Zhang, Jianliang Xu

This report presents a comprehensive view of our vision on the development path of the human-machine symbiotic art creation.

Philosophy

Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level context memory

no code implementations16 Aug 2022 Jingru Zhu, Ya Guo, Geng Sun, Libo Yang, Min Deng, Jie Chen

This study proposes a novel unsupervised domain adaptation semantic segmentation network (MemoryAdaptNet) for the semantic segmentation of HRS imagery.

Pseudo Label Semantic Segmentation +1

OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms

no code implementations11 Aug 2022 Jia-Xin Zhuang, Xiansong Huang, Yang Yang, Jiancong Chen, Yue Yu, Wei Gao, Ge Li, Jie Chen, Tong Zhang

In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms.

Image Classification Medical Image Classification +2

Neural Optimization Machine: A Neural Network Approach for Optimization

no code implementations8 Aug 2022 Jie Chen, Yongming Liu

The NN objective function can have arbitrary architectures and activation functions.

Multiobjective Optimization

Event-triggered Consensus Control of Heterogeneous Multi-agent Systems: Model- and Data-based Analysis

no code implementations1 Aug 2022 Xin Wang, Jian Sun, Gang Wang, Jie Chen

This article deals with model- and data-based consensus control of heterogenous leader-following multi-agent systems (MASs) under an event-triggering transmission scheme.

Locality Guidance for Improving Vision Transformers on Tiny Datasets

1 code implementation20 Jul 2022 Kehan Li, Runyi Yu, Zhennan Wang, Li Yuan, Guoli Song, Jie Chen

Therefore, our locality guidance approach is very simple and efficient, and can serve as a basic performance enhancement method for VTs on tiny datasets.

NDF: Neural Deformable Fields for Dynamic Human Modelling

1 code implementation19 Jul 2022 Ruiqi Zhang, Jie Chen

However, the learned canonical representation is static and the current design of the deformation fields is not able to represent large movements or detailed geometry changes.

Data-driven Self-triggered Control via Trajectory Prediction

no code implementations18 Jul 2022 Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen

Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity.

Trajectory Prediction

A Survey of Decision Making in Adversarial Games

no code implementations16 Jul 2022 Xiuxian Li, Min Meng, Yiguang Hong, Jie Chen

Game theory has by now found numerous applications in various fields, including economics, industry, jurisprudence, and artificial intelligence, where each player only cares about its own interest in a noncooperative or cooperative manner, but without obvious malice to other players.

Decision Making Jurisprudence

A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion

1 code implementation15 Jul 2022 Junkun Jiang, Jie Chen, Yike Guo

In order to demonstrate the proposed model's capability in dealing with severe data loss scenarios, we contribute a high-accuracy and challenging motion capture dataset of multi-person interactions with severe occlusion.

Using Model-Based Trees with Boosting to Fit Low-Order Functional ANOVA Models

no code implementations14 Jul 2022 Linwei Hu, Jie Chen, Vijayan N. Nair

We propose a new algorithm, called GAMI-Tree, that is similar to EBM, but has a number of features that lead to better performance.

BIG-bench Machine Learning Interpretable Machine Learning

Adaptive Random Fourier Features Kernel LMS

no code implementations14 Jul 2022 Wei Gao, Jie Chen, Cédric Richard, Wentao Shi, Qunfei Zhang

We propose the adaptive random Fourier features Gaussian kernel LMS (ARFF-GKLMS).

Shapley Computations Using Surrogate Model-Based Trees

no code implementations11 Jul 2022 Zhipu Zhou, Jie Chen, Linwei Hu

Shapley-related techniques have gained attention as both global and local interpretation tools because of their desirable properties.

$L_2$BN: Enhancing Batch Normalization by Equalizing the $L_2$ Norms of Features

no code implementations6 Jul 2022 Zhennan Wang, Kehan Li, Runyi Yu, Yian Zhao, Pengchong Qiao, Fan Xu, Guoli Song, Jie Chen

In this paper, we show that the difference in $l_2$ norms of sample features can hinder batch normalization from obtaining more distinguished inter-class features and more compact intra-class features.

Acoustic Scene Classification Image Classification +1

Bridging Mean-Field Games and Normalizing Flows with Trajectory Regularization

no code implementations30 Jun 2022 Han Huang, Jiajia Yu, Jie Chen, Rongjie Lai

In this work, we unravel the connections between MFGs and NFs by contextualizing the training of an NF as solving the MFG.

Integration of Physics-Based and Data-Driven Models for Hyperspectral Image Unmixing

1 code implementation11 Jun 2022 Jie Chen, Min Zhao, Xiuheng Wang, Cédric Richard, Susanto Rahardja

Spectral unmixing is one of the most important quantitative analysis tasks in hyperspectral data processing.

Hyperspectral Unmixing

Joint learning of object graph and relation graph for visual question answering

no code implementations9 May 2022 Hao Li, Xu Li, Belhal Karimi, Jie Chen, Mingming Sun

Modeling visual question answering(VQA) through scene graphs can significantly improve the reasoning accuracy and interpretability.

Question Answering Visual Question Answering

Performance and Interpretability Comparisons of Supervised Machine Learning Algorithms: An Empirical Study

no code implementations27 Apr 2022 Alice J. Liu, Arpita Mukherjee, Linwei Hu, Jie Chen, Vijayan N. Nair

Overall, XGB and FFNNs were competitive, with FFNNs showing better performance in smooth models and tree-based boosting algorithms performing better in non-smooth models.

BIG-bench Machine Learning

ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval

no code implementations CVPR 2022 Mengjun Cheng, Yipeng Sun, Longchao Wang, Xiongwei Zhu, Kun Yao, Jie Chen, Guoli Song, Junyu Han, Jingtuo Liu, Errui Ding, Jingdong Wang

Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable information to understand the visual semantics.

Contrastive Learning Cross-Modal Retrieval +1

Training-free Transformer Architecture Search

1 code implementation CVPR 2022 Qinqin Zhou, Kekai Sheng, Xiawu Zheng, Ke Li, Xing Sun, Yonghong Tian, Jie Chen, Rongrong Ji

Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks.

Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily

no code implementations19 Mar 2022 Jie Chen, Shouzhen Chen, Junbin Gao, Zengfeng Huang, Junping Zhang, Jian Pu

Moreover, we propose a Conv-Agnostic GNNs framework (CAGNNs) to enhance the performance of GNNs on heterophily datasets by learning the neighbor effect for each node.

Node Classification

Data-Efficient Graph Grammar Learning for Molecular Generation

1 code implementation ICLR 2022 Minghao Guo, Veronika Thost, Beichen Li, Payel Das, Jie Chen, Wojciech Matusik

This is a non-trivial task for neural network-based generative models since the relevant chemical knowledge can only be extracted and generalized from the limited training data.

Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning

no code implementations25 Feb 2022 Feifei Shao, Yawei Luo, Ping Liu, Jie Chen, Yi Yang, Yulei Lu, Jun Xiao

To deploy SSDR-AL in a more practical scenario, we design a noise-aware iterative labeling strategy to confront the "noisy annotation" problem introduced by the previous "dominant labeling" strategy in superpoints.

Active Learning Semantic Segmentation

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

1 code implementation ICLR 2022 Enyan Dai, Jie Chen

Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks.

Density Estimation Time Series +1

Model-Based and Data-Driven Control of Event- and Self-Triggered Discrete-Time LTI Systems

no code implementations16 Feb 2022 Xin Wang, Julian Berberich, Jian Sun, Gang Wang, Frank Allgöwer, Jie Chen

To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional approach, through which a model-based stability condition is derived.

STS

Time-Frequency Mask Aware Bi-directional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation

no code implementations9 Feb 2022 Jie Chen, Chang Liu, Jiawu Xie, Jie An, Nan Huang

In particular, this method breaks through the limitations of the existing methods, not only achieves good results in multivariate separation, but also effectively separates signals when mixed with 40dB Gaussian noise signals.

Temporal Sequences

Memory-based Message Passing: Decoupling the Message for Propogation from Discrimination

1 code implementation1 Feb 2022 Jie Chen, Weiqi Liu, Jian Pu

Based on the homophily assumption, the current message passing always aggregates features of connected nodes, such as the graph Laplacian smoothing process.

Graph Representation Learning

Hyperspectral Image Super-resolution with Deep Priors and Degradation Model Inversion

1 code implementation24 Jan 2022 Xiuheng Wang, Jie Chen, Cédric Richard

To overcome inherent hardware limitations of hyperspectral imaging systems with respect to their spatial resolution, fusion-based hyperspectral image (HSI) super-resolution is attracting increasing attention.

Hyperspectral Image Super-Resolution Image Super-Resolution

Geometry-Aware Guided Loss for Deep Crack Recognition

no code implementations CVPR 2022 Zhuangzhuang Chen, Jin Zhang, Zhuonan Lai, Jie Chen, Zun Liu, Jianqiang Li

Despite the substantial progress of deep models for crack recognition, due to the inconsistent cracks in varying sizes, shapes, and noisy background textures, there still lacks the discriminative power of the deeply learned features when supervised by the cross-entropy loss.

Robust Recommendation with Implicit Feedback via Eliminating the Effects of Unexpected Behaviors

1 code implementation21 Dec 2021 Jie Chen, Lifen Jiang, Chunmei Ma, Huazhi Sun

In this paper, we propose a Multi-Preferences Model (MPM) to eliminate the effects of unexpected behaviors.

Recommendation Systems

Mean-Square Stability and Stabilizability Analyses of LTI Systems Under Spatially Correlated Multiplicative Perturbations

no code implementations10 Dec 2021 Jianqi Chen, Tian Qi, Jie Chen

In this paper, we investigate the mean-square stability and stabilizability problems for linear time-invariant systems under stochastic spatially correlated multiplicative uncertainties.

Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning

no code implementations25 Nov 2021 Xiaoxiao Zhao, Jinlong Lei, Li Li, Jie Chen

This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns.

Multi-agent Reinforcement Learning reinforcement-learning +2

Learning Representation for Clustering via Prototype Scattering and Positive Sampling

1 code implementation23 Nov 2021 Zhizhong Huang, Jie Chen, Junping Zhang, Hongming Shan

The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness.

Contrastive Learning Deep Clustering +2

Traversing the Local Polytopes of ReLU Neural Networks

no code implementations AAAI Workshop AdvML 2022 Shaojie Xu, Joel Vaughan, Jie Chen, Aijun Zhang, Agus Sudjianto

Our polytope traversing algorithm can be adapted to a wide range of applications related to robustness and interpretability.

Temporal-MPI: Enabling Multi-Plane Images for Dynamic Scene Modelling via Temporal Basis Learning

no code implementations20 Nov 2021 Wenpeng Xing, Jie Chen

One of the seminal image-based rendering method, the multi-plane image (MPI), produces high novel-view synthesis quality for static scenes.

Novel View Synthesis

Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification

no code implementations17 Nov 2021 Shaojie Xu, Joel Vaughan, Jie Chen, Aijun Zhang, Agus Sudjianto

Although neural networks (NNs) with ReLU activation functions have found success in a wide range of applications, their adoption in risk-sensitive settings has been limited by the concerns on robustness and interpretability.

Distributed stochastic proximal algorithm with random reshuffling for non-smooth finite-sum optimization

no code implementations6 Nov 2021 Xia Jiang, Xianlin Zeng, Jian Sun, Jie Chen, Lihua Xie

We prove that local variable estimates generated by the proposed algorithm achieve consensus and are attracted to a neighborhood of the optimal solution in expectation with an $\mathcal{O}(\frac{1}{T}+\frac{1}{\sqrt{T}})$ convergence rate, where $T$ is the total number of iterations.

Data-driven Hedging of Stock Index Options via Deep Learning

no code implementations5 Nov 2021 Jie Chen, Lingfei Li

We develop deep learning models to learn the hedge ratio for S&P500 index options directly from options data.

Data-driven Control of Dynamic Event-triggered Systems with Delays

no code implementations25 Oct 2021 Xin Wang, Jian Sun, Julian Berberich, Gang Wang, Frank Allgöwer, Jie Chen

Data-based representations for time-invariant linear systems with known or unknown system input matrices are first developed, along with a novel class of dynamic triggering schemes for sampled-data systems with time delays.

Data-Driven Resilient Predictive Control under Denial-of-Service

no code implementations25 Oct 2021 Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen

Finally, a numerical example is given to validate the effectiveness of the proposed control method.

Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining

1 code implementation16 Oct 2021 Tim Kaler, Nickolas Stathas, Anne Ouyang, Alexandros-Stavros Iliopoulos, Tao B. Schardl, Charles E. Leiserson, Jie Chen

Improving the training and inference performance of graph neural networks (GNNs) is faced with a challenge uncommon in general neural networks: creating mini-batches requires a lot of computation and data movement due to the exponential growth of multi-hop graph neighborhoods along network layers.

Deep Encryption: Protecting Pre-Trained Neural Networks with Confusion Neurons

no code implementations29 Sep 2021 Mengbiao Zhao, Shixiong Xu, Jianlong Chang, Lingxi Xie, Jie Chen, Qi Tian

Having consumed huge amounts of training data and computational resource, large-scale pre-trained models are often considered key assets of AI service providers.

Federated Inference through Aligning Local Representations and Learning a Consensus Graph

no code implementations29 Sep 2021 Tengfei Ma, Trong Nghia Hoang, Jie Chen

On the top is a federation of the local data representations, performing global inference that incorporates all distributed parts collectively.

Federated Learning

Transient Performance Analysis of the $\ell_1$-RLS

no code implementations14 Sep 2021 Wei Gao, Jie Chen, Cédric Richard, Wentao Shi, Qunfei Zhang

The recursive least-squares algorithm with $\ell_1$-norm regularization ($\ell_1$-RLS) exhibits excellent performance in terms of convergence rate and steady-state error in identification of sparse systems.

Supervised Linear Dimension-Reduction Methods: Review, Extensions, and Comparisons

no code implementations9 Sep 2021 Shaojie Xu, Joel Vaughan, Jie Chen, Agus Sudjianto, Vijayan Nair

Principal component analysis (PCA) is a well-known linear dimension-reduction method that has been widely used in data analysis and modeling.

Dimensionality Reduction

On Faster Convergence of Scaled Sign Gradient Descent

no code implementations4 Sep 2021 Xiuxian Li, Kuo-Yi Lin, Li Li, Yiguang Hong, Jie Chen

For the first two cases, it can be shown that the scaled signGD converges at a linear rate.

An Information Theory-inspired Strategy for Automatic Network Pruning

1 code implementation19 Aug 2021 Xiawu Zheng, Yuexiao Ma, Teng Xi, Gang Zhang, Errui Ding, Yuchao Li, Jie Chen, Yonghong Tian, Rongrong Ji

This practically limits the application of model compression when the model needs to be deployed on a wide range of devices.

AutoML Model Compression +1

Attention-Guided NIR Image Colorization via Adaptive Fusion of Semantic and Texture Clues

no code implementations20 Jul 2021 Xingxing Yang, Jie Chen, Zaifeng Yang, Zhenghua Chen

Finally, a Fusion Attention Block (FAB) is proposed to adaptively fuse the features from the two branches and generate an optimized colorization result.

Colorization Image Colorization

Efficient proximal gradient algorithms for joint graphical lasso

no code implementations16 Jul 2021 Jie Chen, Ryosuke Shimmura, Joe Suzuki

We consider learning an undirected graphical model from sparse data.

Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration

no code implementations13 Jul 2021 Jie Chen, Zaifeng Yang, Tsz Nam Chan, Hui Li, Junhui Hou, Lap-Pui Chau

A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner.

Association Image Restoration

Graph coarsening: From scientific computing to machine learning

no code implementations22 Jun 2021 Jie Chen, Yousef Saad, Zechen Zhang

The general method of graph coarsening or graph reduction has been a remarkably useful and ubiquitous tool in scientific computing and it is now just starting to have a similar impact in machine learning.

BIG-bench Machine Learning

Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification

1 code implementation CVPR 2021 Qiong Wu, Pingyang Dai, Jie Chen, Chia-Wen Lin, Yongjian Wu, Feiyue Huang, Bineng Zhong, Rongrong Ji

In this paper, we propose a joint Modality and Pattern Alignment Network (MPANet) to discover cross-modality nuances in different patterns for visible-infrared person Re-ID, which introduces a modality alleviation module and a pattern alignment module to jointly extract discriminative features.

Person Re-Identification

Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering

no code implementations17 Jun 2021 Wenpeng Xing, Jie Chen, Zaifeng Yang, Qiang Wang

Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence.

Novel View Synthesis

Composition and Application of Current Advanced Driving Assistance System: A Review

no code implementations26 May 2021 Xinran Li, Kuo-Yi Lin, Min Meng, Xiuxian Li, Li Li, Yiguang Hong, Jie Chen

Due to the growing awareness of driving safety and the development of sophisticated technologies, advanced driving assistance system (ADAS) has been equipped in more and more vehicles with higher accuracy and lower price.

CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks

1 code implementation25 May 2021 Ruchir Puri, David S. Kung, Geert Janssen, Wei zhang, Giacomo Domeniconi, Vladimir Zolotov, Julian Dolby, Jie Chen, Mihir Choudhury, Lindsey Decker, Veronika Thost, Luca Buratti, Saurabh Pujar, Shyam Ramji, Ulrich Finkler, Susan Malaika, Frederick Reiss

In addition to its large scale, CodeNet has a rich set of high-quality annotations to benchmark and help accelerate research in AI techniques for a variety of critical coding tasks, including code similarity and classification, code translation between a large variety of programming languages, and code performance (runtime and memory) improvement techniques.

BIG-bench Machine Learning Code Classification +1

Bias, Fairness, and Accountability with AI and ML Algorithms

no code implementations13 May 2021 Nengfeng Zhou, Zach Zhang, Vijayan N. Nair, Harsh Singhal, Jie Chen, Agus Sudjianto

In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms.

Fairness

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

no code implementations11 May 2021 Huihuang Chen, Li Li, Jie Chen, Kuo-Yi Lin

In addition to aligning the global distribution, the real domain adaptation should also align the meso distribution and the micro distribution.

Pseudo Label Unsupervised Domain Adaptation

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

no code implementations10 May 2021 Jianqi Chen, Jieqiang Wei, Wei Chen, Henrik Sandberg, Karl H. Johansson, Jie Chen

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.

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

no code implementations30 Apr 2021 Dongming Yang, Yuexian Zou, Can Zhang, Meng Cao, Jie Chen

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.

Human-Object Interaction Detection

Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification

no code implementations28 Apr 2021 Jie Chen, Shouzhen Chen, Mingyuan Bai, Jian Pu, Junping Zhang, Junbin Gao

In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention.

General Classification Graph Learning +2

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

no code implementations26 Apr 2021 Jie Chen, Jie Liu, Chang Liu, Jian Zhang, Bing Han

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.

Carrying out CNN Channel Pruning in a White Box

1 code implementation24 Apr 2021 Yuxin Zhang, Mingbao Lin, Chia-Wen Lin, Jie Chen, Feiyue Huang, Yongjian Wu, Yonghong Tian, Rongrong Ji

Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w. r. t.

Image Classification

Image-based Virtual Fitting Room

1 code implementation8 Apr 2021 Zhiling Huang, Junwen Bu, Jie Chen

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.

Style Transfer

CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning

1 code implementation CVPR 2021 Can Zhang, Meng Cao, Dongming Yang, Jie Chen, Yuexian Zou

In this paper, we argue that learning by comparing helps identify these hard snippets and we propose to utilize snippet Contrastive learning to Localize Actions, CoLA for short.

CoLA Contrastive Learning +3

Noise Injection-based Regularization for Point Cloud Processing

no code implementations28 Mar 2021 Xiao Zang, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan

In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs.

Data Augmentation Semantic Segmentation

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

no code implementations22 Mar 2021 Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo, Jie Chen

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.

Quantization

Linear Iterative Feature Embedding: An Ensemble Framework for Interpretable Model

no code implementations18 Mar 2021 Agus Sudjianto, Jinwen Qiu, Miaoqi Li, Jie Chen

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.

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

no code implementations12 Mar 2021 Maboud F. Kaloorazi, Jie Chen

The efficiency and effectiveness of our proposed PbP-QLP algorithm are investigated through various classes of synthetic and real-world data matrices.

Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning

1 code implementation1 Mar 2021 Yang Yang, Jiancong Chen, Ruixuan Wang, Ting Ma, Lingwei Wang, Jie Chen, Wei-Shi Zheng, Tong Zhang

Despite tremendous efforts, it is very challenging to generate a robust model to assist in the accurate quantification assessment of COVID-19 on chest CT images.

Performance of Domain-Wall Encoding for Quantum Annealing

no code implementations24 Feb 2021 Jie Chen, Tobias Stollenwerk, Nicholas Chancellor

In this paper we experimentally test the performance of the recently proposed domain-wall encoding of discrete variables from [Chancellor Quantum Sci.

Quantum Physics

Learning Structral coherence Via Generative Adversarial Network for Single Image Super-Resolution

1 code implementation25 Jan 2021 Yuanzhuo Li, Yunan Zheng, Jie Chen, Zhenyu Xu, Yiguang Liu

Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vision system.

Image Restoration Image Super-Resolution +1

Generating a Doppelganger Graph: Resembling but Distinct

1 code implementation23 Jan 2021 Yuliang Ji, Ru Huang, Jie Chen, Yuanzhe Xi

Deep generative models, since their inception, have become increasingly more capable of generating novel and perceptually realistic signals (e. g., images and sound waves).

Graph Representation Learning Node Classification

Discrete Graph Structure Learning for Forecasting Multiple Time Series

1 code implementation ICLR 2021 Chao Shang, Jie Chen, Jinbo Bi

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.

Graph structure learning Time Series Forecasting

Transient Theoretical Analysis of Diffusion RLS Algorithm for Cyclostationary Colored Inputs

no code implementations12 Jan 2021 Wei Gao, Jie Chen, Cédric Richard

Convergence of the diffusion RLS (DRLS) algorithm to steady-state has been extensively studied in the literature, whereas no analysis of its transient convergence behavior has been reported yet.

CDNet: Centripetal Direction Network for Nuclear Instance Segmentation

2 code implementations ICCV 2021 Hongliang He, Zhongyi Huang, Yao Ding, Guoli Song, Lin Wang, Qian Ren, Pengxu Wei, Zhiqiang Gao, Jie Chen

Specifically, we define the centripetal direction feature as a class of adjacent directions pointing to the nuclear center to represent the spatial relationship between pixels within the nucleus.

Instance Segmentation Semantic Segmentation

A Plug-and-Play Priors Framework for Hyperspectral Unmixing

1 code implementation24 Dec 2020 Min Zhao, Xiuheng Wang, Jie Chen, Wei Chen

Spectral unmixing is a widely used technique in hyperspectral image processing and analysis.

Hyperspectral Unmixing Image Denoising

Empirical Evaluation of Typical Sparse Fast Fourier Transform Algorithms

no code implementations15 Dec 2020 Bin Li, Zhikang Jiang, Jie Chen

Computing the Sparse Fast Fourier Transform(sFFT) of a K-sparse signal of size N has emerged as a critical topic for a long time.

Online Convex Optimization Over Erdos-Renyi Random Networks

no code implementations NeurIPS 2020 Jinlong Lei, Peng Yi, Yiguang Hong, Jie Chen, Guodong Shi

The regret bounds scaling with respect to $T$ match those obtained by state-of-the-art algorithms and fundamental limits in the corresponding centralized online optimization problems, e. g., $\mathcal{O}(\sqrt{T}) $ and $\mathcal{O}(\ln(T)) $ regrets are established for convex and strongly convex losses with full gradient feedback and two-points information, respectively.

Handling Noisy Labels via One-Step Abductive Multi-Target Learning: An Application to Helicobacter Pylori Segmentation

no code implementations25 Nov 2020 Yongquan Yang, Yiming Yang, Jie Chen, Jiayi Zheng, Zhongxi Zheng

This situation raises two more difficult problems: 1) the methodology of approaches making corrections corresponding to potentially noisy-labeled instances has limitations due to the complex noise existing in labels; and 2) the appropriate evaluation strategy for validation/testing is unclear because of the great difficulty in collecting the noisy-free ground-truth labels.

Logical Reasoning

Edge Adaptive Hybrid Regularization Model For Image Deblurring

no code implementations20 Nov 2020 Tingting Zhang, Jie Chen, Caiying Wu, Zhifei He, Tieyong Zeng, Qiyu Jin

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.

Deblurring Image Deblurring +2

On Performance of Sparse Fast Fourier Transform Algorithms Using the Aliasing Filter

no code implementations11 Nov 2020 Bin Li, Zhikang Jiang, Jie Chen

In the second part, we make two categories of experiments for computing the signals of different SNR, different N, different K by a standard testing platform and record the run time, percentage of the signal sampled and L0, L1, L2 error both in the exactly sparse case and general sparse case.

On Performance of Multiscale Sparse Fast Fourier Transform Algorithm

no code implementations11 Nov 2020 Bin Li, Zhikang Jiang, Jie Chen

The sFFT algorithms decrease the runtime and sampling complexity by taking advantage of the signal inherent characteristics that a large number of signals are sparse in the frequency domain(e. g., sensors, video data, audio, medical image, etc.).

Deep reinforcement learning for RAN optimization and control

no code implementations9 Nov 2020 Yu Chen, Jie Chen, Ganesh Krishnamurthi, Huijing Yang, Huahui Wang, Wenjie Zhao

Due to the high variability of the traffic in the radio access network (RAN), fixed network configurations are not flexible enough to achieve optimal performance.

reinforcement-learning reinforcement Learning

Multiple-element joint detection for Aspect-Based Sentiment Analysis

no code implementations Knowledge Based Systems 2020 Chao Wu, Qingyu Xiong, Hualing Yi, Yang Yu, Qiwu Zhu, Min Gao, Jie Chen

In this paper, we propose a novel end-to-end multiple-element joint detection model (MEJD), which effectively extracts all (target, aspect, sentiment) triples from a sentence.

Aspect-Based Sentiment Analysis

Hyperspectral Unmixing via Nonnegative Matrix Factorization with Handcrafted and Learnt Priors

no code implementations9 Oct 2020 Min Zhao, Tiande Gao, Jie Chen, Wei Chen

In our work, we propose an NMF based unmixing framework which jointly uses a handcrafting regularizer and a learnt regularizer from data.

Hyperspectral Unmixing

Deep Selective Combinatorial Embedding and Consistency Regularization for Light Field Super-resolution

no code implementations26 Sep 2020 Jing Jin, Junhui Hou, Zhiyu Zhu, Jie Chen, Sam Kwong

To preserve the parallax structure among the reconstructed SAIs, we subsequently append a consistency regularization network trained over a structure-aware loss function to refine the parallax relationships over the coarse estimation.

Disparity Estimation Super-Resolution

A deep learning-based approach for the automated surface inspection of copper clad laminate images

no code implementations19 Sep 2020 Xiaoqing Zheng, Jie Chen, Hongcheng Wang, Song Zheng, Yaguang Kong

A machine vision-based surface quality inspection system is usually composed of two processes: image acquisition and automatic defect detection.

Anomaly Detection Defect Detection

The 1st Tiny Object Detection Challenge:Methods and Results

1 code implementation16 Sep 2020 Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi

The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.

Human Detection object-detection +1

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

1 code implementation9 Sep 2020 Xiuheng Wang, Jie Chen, Qi Wei, Cédric Richard

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.

Hyperspectral Image Super-Resolution Image Super-Resolution

Surrogate Locally-Interpretable Models with Supervised Machine Learning Algorithms

no code implementations28 Jul 2020 Linwei Hu, Jie Chen, Vijayan N. Nair, Agus Sudjianto

Supervised Machine Learning (SML) algorithms, such as Gradient Boosting, Random Forest, and Neural Networks, have become popular in recent years due to their superior predictive performance over traditional statistical methods.

BIG-bench Machine Learning regression

Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms

no code implementations27 Jul 2020 Yanna Bai, Wei Chen, Jie Chen, Weisi Guo

The linear inverse problem is fundamental to the development of various scientific areas.

Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures

1 code implementation ECCV 2020 Mantang Guo, Junhui Hou, Jing Jin, Jie Chen, Lap-Pui Chau

Coded aperture is a promising approach for capturing the 4-D light field (LF), in which the 4-D data are compressively modulated into 2-D coded measurements that are further decoded by reconstruction algorithms.

Image and Video Processing

Online Graph-Based Change Point Detection in Multiband Image Sequences

no code implementations24 Jun 2020 Ricardo Augusto Borsoi, Cédric Richard, André Ferrari, Jie Chen, José Carlos Moreira Bermudez

To effectively perform change-point detection in multitemporal images, it is important to devise techniques that are computationally efficient for processing large datasets, and that do not require knowledge about the nature of the changes.

Change Point Detection

Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning

1 code implementation18 Jun 2020 Zhiyu Zhu, Junhui Hou, Jie Chen, Huanqiang Zeng, Jiantao Zhou

Specifically, PZRes-Net learns a high resolution and \textit{zero-centric} residual image, which contains high-frequency spatial details of the scene across all spectral bands, from both inputs in a progressive fashion along the spectral dimension.

Hyperspectral Image Super-Resolution Hyperspectral Unmixing +1

AnimeGAN: A Novel Lightweight GAN for Photo Animation

2 code implementations International Symposium on Intelligence Computation and Applications 2020 Jie Chen, Gang Liu, Xin Chen

The existing methods usually have some problems, among which significant problems mainly include: 1) the generated images have no obvious animated style textures; 2) the generated images lose the content of the original images; 3) the parameters of the network require the large memory capacity.

Style Transfer

Policy Gradient from Demonstration and Curiosity

no code implementations22 Apr 2020 Jie Chen, Wenjun Xu

In this work, an integrated policy gradient algorithm was proposed to boost exploration and facilitate intrinsic reward learning from only limited number of demonstrations.

Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization

1 code implementation CVPR 2020 Jing Jin, Junhui Hou, Jie Chen, Sam Kwong

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension.

Super-Resolution

Adaptive Explainable Neural Networks (AxNNs)

no code implementations5 Apr 2020 Jie Chen, Joel Vaughan, Vijayan N. Nair, Agus Sudjianto

While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results.

Distributed Computing

Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection

no code implementations CVPR 2020 Jie Chen, Zhiheng Li, Jiebo Luo, Chenliang Xu

Instead of blindly trusting quality-inconsistent PAs, WS^2 employs a learning-based selection to select effective PAs and a novel region integrity criterion as a stopping condition for weakly-supervised training.

Action Segmentation Semantic Segmentation +2

Parallel and distributed asynchronous adaptive stochastic gradient methods

1 code implementation21 Feb 2020 Yangyang Xu, Colin Sutcher-Shepard, Yibo Xu, Jie Chen

The proposed method is tested on both convex and non-convex machine learning problems, and the numerical results demonstrate its clear advantages over the sync counterpart and the async-parallel nonadaptive SGM.

Optimization and Control Distributed, Parallel, and Cluster Computing Numerical Analysis Numerical Analysis 90C15, 65Y05, 68W15, 65K05

Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models

1 code implementation12 Feb 2020 Xiao Zang, Yi Xie, Jie Chen, Bo Yuan

Worse, the bad actors found for one graph model severely compromise other models as well.

Graph Learning

Cooperative Pursuit with Multi-Pursuer and One Faster Free-moving Evader

1 code implementation IEEE Transactions on Cybernetics 2020 Xu Fang, Chen Wang, Lihua Xie, Jie Chen

When the faster evader is allowed to move freely without any constraint, the main issues are how to form an encirclement to trap the evader into the capture domain, how to balance between forming an encirclement and approaching the faster evader, and what conditions make the capture possible.

Systems and Control Systems and Control

Embedding Compression with Isotropic Iterative Quantization

no code implementations11 Jan 2020 Siyu Liao, Jie Chen, Yanzhi Wang, Qinru Qiu, Bo Yuan

Continuous representation of words is a standard component in deep learning-based NLP models.

Image Retrieval Quantization +1

Multitask learning over graphs: An Approach for Distributed, Streaming Machine Learning

no code implementations7 Jan 2020 Roula Nassif, Stefan Vlaski, Cedric Richard, Jie Chen, Ali H. Sayed

Multitask learning is an approach to inductive transfer learning (using what is learned for one problem to assist in another problem) and helps improve generalization performance relative to learning each task separately by using the domain information contained in the training signals of related tasks as an inductive bias.

BIG-bench Machine Learning Inductive Bias +1

Weighted Sum-Rate Maximization for Reconfigurable Intelligent Surface Aided Wireless Networks

2 code implementations27 Dec 2019 Huayan Guo, Ying-Chang Liang, Jie Chen, Erik G. Larsson

Our objective is to maximize the weighted sum-rate (WSR) of all users by joint designing the beamforming at the access point (AP) and the phase vector of the RIS elements, while both the perfect channel state information (CSI) setup and the imperfect CSI setup are investigated.

Signal Processing

Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport

1 code implementation24 Dec 2019 Tengfei Ma, Jie Chen

Both the coarsening matrix and the transport cost matrix are parameterized, so that an optimal coarsening strategy can be learned and tailored for a given set of graphs.

Graph Classification

Chart Auto-Encoders for Manifold Structured Data

no code implementations20 Dec 2019 Stefan Schonsheck, Jie Chen, Rongjie Lai

CAE admits desirable manifold properties that auto-encoders with a flat latent space fail to obey, predominantly proximity of data.

Representation Learning

CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator

no code implementations16 Dec 2019 Huy Phan, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan

In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations.

Adversarial Attack

Scalable Variational Bayesian Kernel Selection for Sparse Gaussian Process Regression

no code implementations5 Dec 2019 Tong Teng, Jie Chen, Yehong Zhang, Kian Hsiang Low

To achieve this, we represent the probabilistic kernel as an additional variational variable in a variational inference (VI) framework for SGPR models where its posterior belief is learned together with that of the other variational variables (i. e., inducing variables and kernel hyperparameters).

regression Stochastic Optimization +1

Graph Enhanced Cross-Domain Text-to-SQL Generation

no code implementations WS 2019 Siyu Huo, Tengfei Ma, Jie Chen, Maria Chang, Lingfei Wu, Michael Witbrock

Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations.

Natural Language Understanding Semantic Parsing +3

DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition

no code implementations28 Oct 2019 Zhao You, Dan Su, Jie Chen, Chao Weng, Dong Yu

Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency.

Automatic Speech Recognition speech-recognition

Unsupervised Hierarchical Graph Representation Learning with Variational Bayes

no code implementations25 Sep 2019 Shashanka Ubaru, Jie Chen

These approaches are supervised; a predictive task with ground-truth labels is used to drive the learning.

Graph Classification Graph Representation Learning

Adaptively Aligned Image Captioning via Adaptive Attention Time

1 code implementation NeurIPS 2019 Lun Huang, Wenmin Wang, Yaxian Xia, Jie Chen

In this paper, we propose a novel attention model, namely Adaptive Attention Time (AAT), to align the source and the target adaptively for image captioning.

Image Captioning

Deep Coarse-to-fine Dense Light Field Reconstruction with Flexible Sampling and Geometry-aware Fusion

1 code implementation31 Aug 2019 Jing Jin, Junhui Hou, Jie Chen, Huanqiang Zeng, Sam Kwong, Jingyi Yu

Specifically, the coarse sub-aperture image (SAI) synthesis module first explores the scene geometry from an unstructured sparsely-sampled LF and leverages it to independently synthesize novel SAIs, in which a confidence-based blending strategy is proposed to fuse the information from different input SAIs, giving an intermediate densely-sampled LF.

Depth Estimation

Attention on Attention for Image Captioning

5 code implementations ICCV 2019 Lun Huang, Wenmin Wang, Jie Chen, Xiao-Yong Wei

In this paper, we propose an Attention on Attention (AoA) module, which extends the conventional attention mechanisms to determine the relevance between attention results and queries.

Image Captioning

Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics

1 code implementation31 Jul 2019 Mark Weber, Giacomo Domeniconi, Jie Chen, Daniel Karl I. Weidele, Claudio Bellei, Tom Robinson, Charles E. Leiserson

We contribute the Elliptic Data Set, a time series graph of over 200K Bitcoin transactions (nodes), 234K directed payment flows (edges), and 166 node features, including ones based on non-public data; to our knowledge, this is the largest labelled transaction data set publicly available in any cryptocurrency.

Time Series

Light Field Super-resolution via Attention-Guided Fusion of Hybrid Lenses

1 code implementation23 Jul 2019 Jing Jin, Junhui Hou, Jie Chen, Sam Kwong, Jingyi Yu

To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-resolution LF image with a hybrid input.

Super-Resolution

Weighted Sum-Rate Optimization for Intelligent Reflecting Surface Enhanced Wireless Networks

2 code implementations20 May 2019 Huayan Guo, Ying-Chang Liang, Jie Chen, Erik G. Larsson

In addition, we consider a practical IRS assumption, in which the passive elements can only shift the incident signal to discrete phase levels.

Learning discriminative features in sequence training without requiring framewise labelled data

no code implementations16 May 2019 Jun Wang, Dan Su, Jie Chen, Shulin Feng, Dongpeng Ma, Na Li, Dong Yu

We propose a novel method which simultaneously models both the sequence discriminative training and the feature discriminative learning within a single network architecture, so that it can learn discriminative deep features in sequence training that obviates the need for presegmented training data.

Hyperspectral Unmixing via Deep Autoencoder Networks for a Generalized Linear-Mixture/Nonlinear-Fluctuation Model

no code implementations30 Apr 2019 Min Zhao, Mou Wang, Jie Chen, Susanto Rahardja

This paper presents an unsupervised nonlinear spectral unmixing method based on a deep autoencoder network that applies to a generalized linear-mixture/nonlinear fluctuation model, consisting of a linear mixture component and an additive nonlinear mixture component that depends on both endmembers and abundances.

Hyperspectral Unmixing

Time Series Simulation by Conditional Generative Adversarial Net

no code implementations25 Apr 2019 Rao Fu, Jie Chen, Shutian Zeng, Yiping Zhuang, Agus Sudjianto

Generative Adversarial Net (GAN) has been proven to be a powerful machine learning tool in image data analysis and generation.

Time Series

DAG-GNN: DAG Structure Learning with Graph Neural Networks

3 code implementations22 Apr 2019 Yue Yu, Jie Chen, Tian Gao, Mo Yu

Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes.

A Sequential Set Generation Method for Predicting Set-Valued Outputs

no code implementations12 Mar 2019 Tian Gao, Jie Chen, Vijil Chenthamarakshan, Michael Witbrock

Though SSG is sequential in nature, it does not penalize the ordering of the appearance of the set elements and can be applied to a variety of set output problems, such as a set of classification labels or sequences.

General Classification Multi-Label Classification

Stratified Labeling for Surface Consistent Parallax Correction and Occlusion Completion

no code implementations7 Mar 2019 Jie Chen, Lap-Pui Chau, Junhui Hou

A stratified synthesis strategy is adopted which parses the scene content based on stratified disparity layers and across a varying range of spatial granularities.

Novel View Synthesis

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

8 code implementations26 Feb 2019 Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B. Schardl, Charles E. Leiserson

Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics.

Dynamic Link Prediction Edge Classification +3

A laboratory-created dataset with ground-truth for hyperspectral unmixing evaluation

no code implementations22 Feb 2019 Min Zhao, Jie Chen, Zhe He

To the best of our knowledge, this dataset is the first publicly available dataset created in a systematic manner with ground-truth for spectral unmixing.

Hyperspectral Unmixing

Scalable Graph Learning for Anti-Money Laundering: A First Look

2 code implementations30 Nov 2018 Mark Weber, Jie Chen, Toyotaro Suzumura, Aldo Pareja, Tengfei Ma, Hiroki Kanezashi, Tim Kaler, Charles E. Leiserson, Tao B. Schardl

Organized crime inflicts human suffering on a genocidal scale: the Mexican drug cartels have murdered 150, 000 people since 2006, upwards of 700, 000 people per year are "exported" in a human trafficking industry enslaving an estimated 40 million people.

Graph Learning

Automatic Seismic Salt Interpretation with Deep Convolutional Neural Networks

1 code implementation24 Nov 2018 Yu Zeng, Kebei Jiang, Jie Chen

One of the most crucial tasks in seismic reflection imaging is to identify the salt bodies with high precision.

Revisiting Random Binning Features: Fast Convergence and Strong Parallelizability

2 code implementations14 Sep 2018 Lingfei Wu, Ian E. H. Yen, Jie Chen, Rui Yan

We thus propose the first analysis of RB from the perspective of optimization, which by interpreting RB as a Randomized Block Coordinate Descent in the infinite-dimensional space, gives a faster convergence rate compared to that of other random features.

Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders

1 code implementation NeurIPS 2018 Tengfei Ma, Jie Chen, Cao Xiao

We focus on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints.

Time Series

Deep Learning for Generic Object Detection: A Survey

no code implementations6 Sep 2018 Li Liu, Wanli Ouyang, Xiaogang Wang, Paul Fieguth, Jie Chen, Xinwang Liu, Matti Pietikäinen

Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images.

object-detection Object Proposal Generation