Search Results for author: Xiang Li

Found 204 papers, 68 papers with code

Gait Recognition from a Single Image using a Phase-Aware Gait Cycle Reconstruction Network

no code implementations ECCV 2020 Chi Xu, Yasushi Makihara, Xiang Li, Yasushi Yagi, Jianfeng Lu

Specifically, a phase estimation network is introduced for the input single image, and the gait cycle reconstruction network exploits the estimated phase to mitigate the dependence of an encoded feature on the phase of that single image.

Gait Recognition

Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings

no code implementations ACL 2022 Shib Dasgupta, Michael Boratko, Siddhartha Mishra, Shriya Atmakuri, Dhruvesh Patel, Xiang Li, Andrew McCallum

In this work, we provide a fuzzy-set interpretation of box embeddings, and learn box representations of words using a set-theoretic training objective.

Word Similarity

Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network

no code implementations ACL 2022 Bin Liang, Chenwei Lou, Xiang Li, Min Yang, Lin Gui, Yulan He, Wenjie Pei, Ruifeng Xu

Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance.

Sarcasm Detection

JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection

1 code implementation ACL 2022 Bin Liang, Qinglin Zhu, Xiang Li, Min Yang, Lin Gui, Yulan He, Ruifeng Xu

In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastive learning and target-aware prototypical graph contrastive learning.

Contrastive Learning Stance Detection

融合情感分析的隐式反问句识别模型(Implicit Rhetorical Questions Recognition Model Combined with Sentiment Analysis)

no code implementations CCL 2021 Xiang Li, Chengwei Liu, Xiaoxu Zhu

“反问是现代汉语中一种常用的修辞手法, 根据是否含有反问标记可分为显式反问句与隐式反问句。其中隐式反问句表达的情感更为丰富, 表现形式也十分复杂, 对隐式反问句的识别更具挑战性。本文首先扩充了汉语反问句语料库, 语料库规模达到10000余句, 接着针对隐式反问句的特点, 提出了一种融合情感分析的隐式反问句识别模型。模型考虑了句子的语义信息, 上下文信息, 并借助情感分析任务辅助识别隐式反问句。实验结果表明, 本文提出的模型在隐式反问句识别任务上取得了良好的性能。”

Sentiment Analysis

AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking System

no code implementations19 May 2022 Xiang Li, Xiaojiang Zhou, Yao Xiao, Peihao Huang, Dayao Chen, Sheng Chen, Yunsen Xian

Industrial search and recommendation systems mostly follow the classic multi-stage information retrieval paradigm: matching, pre-ranking, ranking, and re-ranking stages.

Information Retrieval Neural Architecture Search +2

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

1 code implementation15 May 2022 Xiang Li, Renyu Zhu, Yao Cheng, Caihua Shan, Siqiang Luo, Dongsheng Li, Weining Qian

Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation.

Lexical Knowledge Internalization for Neural Dialog Generation

1 code implementation ACL 2022 Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao

We propose knowledge internalization (KI), which aims to complement the lexical knowledge into neural dialog models.

Contrastive Learning

Speech Emotion Recognition with Global-Aware Fusion on Multi-scale Feature Representation

1 code implementation12 Apr 2022 Wenjing Zhu, Xiang Li

Speech Emotion Recognition (SER) is a fundamental task to predict the emotion label from speech data.

Speech Emotion Recognition

An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer

1 code implementation31 Mar 2022 Wenlin Dai, Changhe Song, Xiang Li, Zhiyong Wu, Huashan Pan, Xiulin Li, Helen Meng

Inspired by Flat-LAttice Transformer (FLAT), we propose an end-to-end Chinese text normalization model, which accepts Chinese characters as direct input and integrates expert knowledge contained in rules into the neural network, both contribute to the superior performance of proposed model for the text normalization task.

PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection

no code implementations30 Mar 2022 Gang Li, Xiang Li, Yujie Wang, Shanshan Zhang, Yichao Wu, Ding Liang

Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance.

Object Detection Semi-Supervised Object Detection

Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search

1 code implementation29 Mar 2022 Zhifang Fan, Dan Ou, Yulong Gu, Bairan Fu, Xiang Li, Wentian Bao, Xin-yu Dai, Xiaoyi Zeng, Tao Zhuang, Qingwen Liu

In this paper, we propose a new perspective for context-aware users' behavior modeling by including the whole page-wisely exposed products and the corresponding feedback as contextualized page-wise feedback sequence.

Click-Through Rate Prediction Denoising

A Learning Convolutional Neural Network Approach for Network Robustness Prediction

no code implementations20 Mar 2022 Yang Lou, Ruizi Wu, Junli Li, Lin Wang, Xiang Li, Guanrong Chen

Extensive experimental studies on both synthetic and real-world networks, both directed and undirected, demonstrate that 1) the proposed LFR-CNN performs better than other two state-of-the-art prediction methods, with significantly lower prediction errors; 2) LFR-CNN is insensitive to the variation of the network size, which significantly extends its applicability; 3) although LFR-CNN needs more time to perform feature learning, it can achieve accurate prediction faster than attack simulations; 4) LFR-CNN not only can accurately predict network robustness, but also provides a good indicator for connectivity robustness, better than the classical spectral measures.

Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion

no code implementations18 Mar 2022 Zhiqiang Yan, Xiang Li, Kun Wang, Zhenyu Zhang, Jun Li, Jian Yang

Specifically, during pre-training, we simultaneously cover up patches of the panoramic RGB image and sparse depth by shared random mask, then reconstruct the sparse depth in the masked regions.

Depth Completion Transfer Learning

EEG based Emotion Recognition: A Tutorial and Review

no code implementations16 Mar 2022 Xiang Li, Yazhou Zhang, Prayag Tiwari, Dawei Song, Bin Hu, Meihong Yang, Zhigang Zhao, Neeraj Kumar, Pekka Marttinen

Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic.

EEG Emotion Recognition

RecursiveMix: Mixed Learning with History

1 code implementation14 Mar 2022 Lingfeng Yang, Xiang Li, Borui Zhao, RenJie Song, Jian Yang

In semantic segmentation, RM also surpasses the baseline and CutMix by 1. 9 and 1. 1 mIoU points under UperNet on ADE20K, respectively.

Object Detection Semantic Segmentation

Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information

1 code implementation7 Mar 2022 Lingfeng Yang, Xiang Li, RenJie Song, Borui Zhao, Juntian Tao, Shihao Zhou, Jiajun Liang, Jian Yang

Therefore, it is helpful to leverage additional information, e. g., the locations and dates for data shooting, which can be easily accessible but rarely exploited.

Fine-Grained Image Classification

WSLRec: Weakly Supervised Learning for Neural Sequential Recommendation Models

no code implementations28 Feb 2022 Jingwei Zhuo, Bin Liu, Xiang Li, Han Zhu, Xiaoqiang Zhu

Motivated by the observation that model-free methods like behavioral retargeting (BR) and item-based collaborative filtering (ItemCF) hit different parts of the user-item relevance compared to neural sequential recommendation models, we propose a novel model-agnostic training approach called WSLRec, which adopts a three-stage framework: pre-training, top-$k$ mining, and fine-tuning.

Collaborative Filtering Sequential Recommendation

Multi-modal Sensor Fusion for Auto Driving Perception: A Survey

no code implementations6 Feb 2022 Keli Huang, Botian Shi, Xiang Li, Xin Li, Siyuan Huang, Yikang Li

Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers.

Autonomous Driving Object Detection +1

Forgery Attack Detection in Surveillance Video Streams Using Wi-Fi Channel State Information

no code implementations24 Jan 2022 Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang

The cybersecurity breaches expose surveillance video streams to forgery attacks, under which authentic streams are falsified to hide unauthorized activities.

Time Series Video Forensics

Collaborative Reflection-Augmented Autoencoder Network for Recommender Systems

1 code implementation10 Jan 2022 Lianghao Xia, Chao Huang, Yong Xu, Huance Xu, Xiang Li, WeiGuo Zhang

As the deep learning techniques have expanded to real-world recommendation tasks, many deep neural network based Collaborative Filtering (CF) models have been developed to project user-item interactions into latent feature space, based on various neural architectures, such as multi-layer perceptron, auto-encoder and graph neural networks.

Collaborative Filtering Recommendation Systems

Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning

no code implementations31 Dec 2021 Xiang Li, Dong Li, Ruoming Jin, Gagan Agrawal, Rajiv Ramnath

Though other methods (particularly those based on Laplacian Smoothing) have reported better accuracy, a fundamental limitation of all the work is a lack of scalability.

Deep Clustering Graph Clustering +2

Polyak-Ruppert-Averaged Q-Learning is Statistically Efficient

no code implementations29 Dec 2021 Xiang Li, Wenhao Yang, Jiadong Liang, Zhihua Zhang, Michael I. Jordan

We study synchronous Q-learning with Polyak-Ruppert averaging (a. k. a., averaged Q-learning) in a $\gamma$-discounted MDP.

Q-Learning

Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation

no code implementations9 Dec 2021 Gang Li, Xiang Li, Yujie Wang, Shanshan Zhang, Yichao Wu, Ding Liang

Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively.

Knowledge Distillation Model Compression +1

Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentation

no code implementations3 Dec 2021 Xiang Li, Jinglu Wang, Xiao Li, Yan Lu

Based on this representation, we introduce a cropping-free temporal fusion approach to model the temporal consistency between video frames.

Frame Instance Segmentation +2

Reinforcement Learning Enhanced Explainer for Graph Neural Networks

no code implementations NeurIPS 2021 Caihua Shan, Yifei Shen, Yao Zhang, Xiang Li, Dongsheng Li

To address these issues, we propose a RL-enhanced GNN explainer, RG-Explainer, which consists of three main components: starting point selection, iterative graph generation and stopping criteria learning.

Combinatorial Optimization Graph Generation +1

Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network

no code implementations10 Nov 2021 Yi Lin, Jianchao Su, Xiang Wang, Xiang Li, Jingen Liu, Kwang-Ting Cheng, Xin Yang

We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78. 9%, 80. 7% and 80. 7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods.

Pulmonary Embolism Detection

Generative Dynamic Patch Attack

1 code implementation8 Nov 2021 Xiang Li, Shihao Ji

Extensive experiments on VGGFace, Traffic Sign and ImageNet show that GDPA achieves higher attack success rates than state-of-the-art patch attacks, while adversarially trained model with GDPA demonstrates superior robustness to adversarial patch attacks than competing methods.

Improved Loss Function-Based Prediction Method of Extreme Temperatures in Greenhouses

no code implementations2 Nov 2021 Liao Qu, Shuaiqi Huang, Yunsong Jia, Xiang Li

By increasing the weight of extreme temperature samples and reducing the possibility of misjudging extreme temperature as normal, the proposed loss function can enhance the prediction results in extreme situations.

Unified Style Transfer

1 code implementation20 Oct 2021 Guanjie Huang, Hongjian He, Xiang Li, Xingchen Li, Ziang Liu

Currently, it is hard to compare and evaluate different style transfer algorithms due to chaotic definitions of style and the absence of agreed objective validation methods in the study of style transfer.

Style Transfer Translation

Video Instance Segmentation by Instance Flow Assembly

no code implementations20 Oct 2021 Xiang Li, Jinglu Wang, Xiao Li, Yan Lu

Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes.

Frame Instance Segmentation +3

Feasible Architecture for Quantum Fully Convolutional Networks

no code implementations5 Oct 2021 Yusui Chen, Wenhao Hu, Xiang Li

Fully convolutional networks are robust in performing semantic segmentation, with many applications from signal processing to computer vision.

Semantic Segmentation

Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation

no code implementations1 Oct 2021 Zheng Li, Xiang Li, Lingfeng Yang, Jian Yang, Zhigeng Pan

Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm.

Self-Knowledge Distillation

Fine-Grained Few Shot Learning with Foreground Object Transformation

no code implementations13 Sep 2021 Chaofei Wang, Shiji Song, Qisen Yang, Xiang Li, Gao Huang

As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks.

Data Augmentation Few-Shot Learning +1

Cost-Effective Federated Learning in Mobile Edge Networks

no code implementations12 Sep 2021 Bing Luo, Xiang Li, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas

Federated learning (FL) is a distributed learning paradigm that enables a large number of mobile devices to collaboratively learn a model under the coordination of a central server without sharing their raw data.

Federated Learning

RigNet: Repetitive Image Guided Network for Depth Completion

no code implementations29 Jul 2021 Zhiqiang Yan, Kun Wang, Xiang Li, Zhenyu Zhang, Baobei Xu, Jun Li, Jian Yang

Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task.

Depth Completion Depth Estimation

Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes

no code implementations7 Jul 2021 Xiang Li, Lingjing Wang, Yi Fang

To achieve this, we treat the shape segmentation as a point labeling problem in the metric space.

Meta-Learning

A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning

no code implementations28 Jun 2021 Wenchao Zhang, Chong Fu, Xiangshi Chang, Tengfei Zhao, Xiang Li, Chiu-Wing Sham

Without losing generality, we can also build a more lighter head network for other multi-stage detectors by assembling our method.

Object Detection Relational Reasoning

Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding

no code implementations20 Jun 2021 Chaolei Tan, Zihang Lin, Jian-Fang Hu, Xiang Li, Wei-Shi Zheng

We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task.

Frame Spatio-Temporal Video Grounding

The Image Local Autoregressive Transformer

1 code implementation NeurIPS 2021 Chenjie Cao, Yuxin Hong, Xiang Li, Chengrong Wang, Chengming Xu, xiangyang xue, Yanwei Fu

To address these limitations, we propose a novel model -- image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis.

Image Generation

Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning

no code implementations31 May 2021 Binbin Xie, Jinsong Su, Yubin Ge, Xiang Li, Jianwei Cui, Junfeng Yao, Bin Wang

However, such a decoder only exploits the preorder traversal based preceding actions, which are insufficient to ensure correct action predictions.

Code Generation

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation

no code implementations ACL 2021 Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao

A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information.

Multimodal Machine Translation Translation

PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text

1 code implementation2 May 2021 Wenhai Wang, Enze Xie, Xiang Li, Xuebo Liu, Ding Liang, Zhibo Yang, Tong Lu, Chunhua Shen

By systematically comparing with existing scene text representations, we show that our kernel representation can not only describe arbitrarily-shaped text but also well distinguish adjacent text.

Scene Text Detection Text Spotting

Deep Attributed Network Representation Learning via Attribute Enhanced Neighborhood

no code implementations12 Apr 2021 Cong Li, Min Shi, Bo Qu, Xiang Li

In this paper, we propose a deep attributed network representation learning via attribute enhanced neighborhood (DANRL-ANE) model to improve the robustness and effectiveness of node representations.

Link Prediction Node Classification +1

Towards Multi-Scale Style Control for Expressive Speech Synthesis

no code implementations8 Apr 2021 Xiang Li, Changhe Song, Jingbei Li, Zhiyong Wu, Jia Jia, Helen Meng

This paper introduces a multi-scale speech style modeling method for end-to-end expressive speech synthesis.

Expressive Speech Synthesis Style Transfer

Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection

no code implementations21 Mar 2021 Varun Buch, Aoxiao Zhong, Xiang Li, Marcio Aloisio Bezerra Cavalcanti Rockenbach, Dufan Wu, Hui Ren, Jiahui Guan, Andrew Liteplo, Sayon Dutta, Ittai Dayan, Quanzheng Li

Predictive risk scores for COVID-19 severe outcomes ("CO-RISK" score) were derived from model output and evaluated on the testing dataset, as well as compared to human performance.

Structure-Enhanced Meta-Learning For Few-Shot Graph Classification

1 code implementation5 Mar 2021 Shunyu Jiang, Fuli Feng, Weijian Chen, Xiang Li, Xiangnan He

Graph classification is a highly impactful task that plays a crucial role in a myriad of real-world applications such as molecular property prediction and protein function prediction. Aiming to handle the new classes with limited labeled graphs, few-shot graph classification has become a bridge of existing graph classification solutions and practical usage. This work explores the potential of metric-based meta-learning for solving few-shot graph classification. We highlight the importance of considering structural characteristics in the solution and propose a novel framework which explicitly considers global structure and local structure of the input graph.

Classification General Classification +4

Privacy-Preserving Distributed SVD via Federated Power

no code implementations1 Mar 2021 Xiao Guo, Xiang Li, Xiangyu Chang, Shusen Wang, Zhihua Zhang

The low communication and computation power of such devices, and the possible privacy breaches of users' sensitive data make the computation of SVD challenging.

Federated Learning

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

9 code implementations ICCV 2021 Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao

Unlike the recently-proposed Transformer model (e. g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer~(PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks.

Image Classification Instance Segmentation +2

vrCAPTCHA: Exploring CAPTCHA Designs in Virtual Reality

no code implementations24 Feb 2021 Xiang Li, Yuzheng Chen, Rakesh Patibanda, Florian 'Floyd' Mueller

With the popularity of online access in virtual reality (VR) devices, it will become important to investigate exclusive and interactive CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) designs for VR devices.

Human-Computer Interaction

SceneRec: Scene-Based Graph Neural Networks for Recommender Systems

no code implementations12 Feb 2021 Gang Wang, Ziyi Guo, Xiang Li, Dawei Yin, Shuai Ma

Collaborative filtering has been largely used to advance modern recommender systems to predict user preference.

Collaborative Filtering Recommendation Systems +1

Delayed Projection Techniques for Linearly Constrained Problems: Convergence Rates, Acceleration, and Applications

no code implementations5 Jan 2021 Xiang Li, Zhihua Zhang

In this work, we study a novel class of projection-based algorithms for linearly constrained problems (LCPs) which have a lot of applications in statistics, optimization, and machine learning.

Distributed Optimization

Towards Cross-Modal Forgery Detection and Localization on Live Surveillance Videos

no code implementations4 Jan 2021 Yong Huang, Xiang Li, Wei Wang, Tao Jiang, Qian Zhang

Traditional video forensics approaches can detect and localize forgery traces in each video frame using computationally-expensive spatial-temporal analysis, while falling short in real-time verification of live video feeds.

Time Series Video Forensics Cryptography and Security

Box-To-Box Transformation for Modeling Joint Hierarchies

no code implementations1 Jan 2021 Shib Sankar Dasgupta, Xiang Li, Michael Boratko, Dongxu Zhang, Andrew McCallum

In Patel et al. (2020), the authors demonstrate that only the transitive reduction is required, and further extend box embeddings to capture joint hierarchies by augmenting the graph with new nodes.

Knowledge Graphs

Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More

1 code implementation1 Jan 2021 Xiulong Yang, Hui Ye, Yang Ye, Xiang Li, Shihao Ji

We show that our Generative MMC (GMMC) can be trained discriminatively, generatively, or jointly for image classification and generation.

Adversarial Robustness Classification +4

Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks

no code implementations18 Dec 2020 Xiang Li, Danhao Ding, Ben Kao, Yizhou Sun, Nikos Mamoulis

A heterogeneous information network (HIN) has as vertices objects of different types and as edges the relations between objects, which are also of various types.

Classification General Classification +2

Cost-Effective Federated Learning Design

no code implementations15 Dec 2020 Bing Luo, Xiang Li, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas

In this paper, we analyze how to design adaptive FL that optimally chooses these essential control variables to minimize the total cost while ensuring convergence.

Federated Learning

Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-Time Sampling

1 code implementation6 Dec 2020 Jia-Qi Yang, Xiang Li, Shuguang Han, Tao Zhuang, De-Chuan Zhan, Xiaoyi Zeng, Bin Tong

To strike a balance in this trade-off, we propose Elapsed-Time Sampling Delayed Feedback Model (ES-DFM), which models the relationship between the observed conversion distribution and the true conversion distribution.

online learning

Physics Guided Machine Learning Methods for Hydrology

no code implementations2 Dec 2020 Ankush Khandelwal, Shaoming Xu, Xiang Li, Xiaowei Jia, Michael Stienbach, Christopher Duffy, John Nieber, Vipin Kumar

The goal of this work is to incorporate our understanding of physical processes and constraints in hydrology into machine learning algorithms, and thus bridge the performance gap while reducing the need for large amounts of data compared to traditional data-driven approaches.

Neuron-level Structured Pruning using Polarization Regularizer

1 code implementation NeurIPS 2020 Tao Zhuang, Zhixuan Zhang, Yuheng Huang, Xiaoyi Zeng, Kai Shuang, Xiang Li

Experimentally, we show that structured pruning using polarization regularizer achieves much better results than using L1 regularizer.

Deep Metric Learning-based Image Retrieval System for Chest Radiograph and its Clinical Applications in COVID-19

no code implementations26 Nov 2020 Aoxiao Zhong, Xiang Li, Dufan Wu, Hui Ren, Kyungsang Kim, YoungGon Kim, Varun Buch, Nir Neumark, Bernardo Bizzo, Won Young Tak, Soo Young Park, Yu Rim Lee, Min Kyu Kang, Jung Gil Park, Byung Seok Kim, Woo Jin Chung, Ning Guo, Ittai Dayan, Mannudeep K. Kalra, Quanzheng Li

These results demonstrate our deep metric learning based image retrieval model is highly efficient in the CXR retrieval, diagnosis and prognosis, and thus has great clinical value for the treatment and management of COVID-19 patients.

Image Retrieval Metric Learning

PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data

1 code implementation16 Nov 2020 Yufeng Wang, Dan Li, Xiang Li, Min Yang

Further, this classifier is incorporated into the generative adversarial framework to help the generator to yield higher quality imputation results.

Imputation

Retrieving and ranking short medical questions with two stages neural matching model

no code implementations16 Nov 2020 Xiang Li, Xinyu Fu, Zheng Lu, Ruibin Bai, Uwe Aickelin, Peiming Ge, Gong Liu

Internet hospital is a rising business thanks to recent advances in mobile web technology and high demand of health care services.

Information Retrieval

3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds

no code implementations22 Oct 2020 Lingjing Wang, Yu Hao, Xiang Li, Yi Fang

In this paper, we propose a meta-learning based 3D registration model, named 3D Meta-Registration, that is capable of rapidly adapting and well generalizing to new 3D registration tasks for unseen 3D point clouds.

Meta-Learning Point Cloud Registration

3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence

no code implementations21 Oct 2020 Hao Huang, Lingjing Wang, Xiang Li, Yi Fang

In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes.

3D Dense Shape Correspondence Meta-Learning

Reading Comprehension as Natural Language Inference: A Semantic Analysis

no code implementations4 Oct 2020 Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula

We transform the one of the largest available MRC dataset (RACE) to an NLI form, and compare the performances of a state-of-the-art model (RoBERTa) on both these forms.

Natural Language Inference Question Answering +1

Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector

no code implementations29 Sep 2020 Lingjing Wang, Xiang Li, Yi Fang

Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation.

Point Cloud Registration

Looking Beyond Sentence-Level Natural Language Inference for Downstream Tasks

no code implementations18 Sep 2020 Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi, Kartik Talamadupula

In recent years, the Natural Language Inference (NLI) task has garnered significant attention, with new datasets and models achieving near human-level performance on it.

Natural Language Inference Question Answering +1

Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration

no code implementations11 Sep 2020 Xiang Li, Lingjing Wang, Yi Fang

To bridge the performance gaps between partial point set registration with full point set registration, we proposed to incorporate a shape completion network to benefit the registration process.

Object Detection in the Context of Mobile Augmented Reality

no code implementations15 Aug 2020 Xiang Li, Yuan Tian, Fuyao Zhang, Shuxue Quan, Yi Xu

Ordinary object detection approaches process information from the images only, and they are oblivious to the camera pose with regard to the environment and the scale of the environment.

Real-Time Object Detection

Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Data

1 code implementation14 Aug 2020 Bin Gu, Zhiyuan Dang, Xiang Li, Heng Huang

In this paper, we focus on nonlinear learning with kernels, and propose a federated doubly stochastic kernel learning (FDSKL) algorithm for vertically partitioned data.

Federated Learning

Robust Image Matching By Dynamic Feature Selection

no code implementations13 Aug 2020 Hao Huang, Jianchun Chen, Xiang Li, Lingjing Wang, Yi Fang

Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching.

Decision Making Frame

GP-Aligner: Unsupervised Non-rigid Groupwise Point Set Registration Based On Optimized Group Latent Descriptor

no code implementations25 Jul 2020 Lingjing Wang, Xiang Li, Yi Fang

More specifically, for a given group we first define an optimizable Group Latent Descriptor (GLD) to characterize the gruopwise relationship among a group of point sets.

Simulating multi-exit evacuation using deep reinforcement learning

no code implementations11 Jul 2020 Dong Xu, Xiao Huang, Joseph Mango, Xiang Li, Zhenlong Li

We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which involves in a Deep Neural Network (DNN) framework to facilitate state-to-action mapping.

reinforcement-learning

Xiaomi's Submissions for IWSLT 2020 Open Domain Translation Task

no code implementations WS 2020 Yuhui Sun, Mengxue Guo, Xiang Li, Jianwei Cui, Bin Wang

This paper describes the Xiaomi{'}s submissions to the IWSLT20 shared open domain translation task for Chinese{\textless}-{\textgreater}Japanese language pair.

Domain Adaptation Knowledge Distillation +2

DeepTracking-Net: 3D Tracking with Unsupervised Learning of Continuous Flow

no code implementations24 Jun 2020 Shuaihang Yuan, Xiang Li, Yi Fang

In this paper, we aim at handling the problem of 3D tracking, which provides the tracking of the consecutive frames of 3D shapes.

3DMotion-Net: Learning Continuous Flow Function for 3D Motion Prediction

no code implementations24 Jun 2020 Shuaihang Yuan, Xiang Li, Anthony Tzes, Yi Fang

To approach this problem, we propose a self-supervised approach that leverages the power of the deep neural network to learn a continuous flow function of 3D point clouds that can predict temporally consistent future motions and naturally bring out the correspondences among consecutive point clouds at the same time.

Frame motion prediction

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

2 code implementations19 Jun 2020 Yu Zheng, Chen Gao, Xiang Li, Xiangnan He, Depeng Jin, Yong Li

We further demonstrate that the learned embeddings successfully capture the desired causes, and show that DICE guarantees the robustness and interpretability of recommendation.

Causal Inference

Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds

no code implementations17 Jun 2020 Lingjing Wang, Yi Shi, Xiang Li, Yi Fang

Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets.

Few-shot Object Detection on Remote Sensing Images

no code implementations14 Jun 2020 Jingyu Deng, Xiang Li, Yi Fang

In this paper, we introduce a few-shot learning-based method for object detection on remote sensing images where only a few annotated samples are provided for the unseen object categories.

Few-Shot Learning Few-Shot Object Detection

Unsupervised Learning of 3D Point Set Registration

no code implementations11 Jun 2020 Lingjing Wang, Xiang Li, Yi Fang

Moreover, for a pair of source and target point sets, existing deep learning mechanisms require explicitly designed encoders to extract both deep spatial features from unstructured point clouds and their spatial correlation representation, which is further fed to a decoder to regress the desired geometric transformation for point set alignment.

Point Cloud Registration

Geometry-Aware Segmentation of Remote Sensing Images via Implicit Height Estimation

no code implementations10 Jun 2020 Xiang Li, Lingjing Wang, Yi Fang

Recent studies have shown the benefits of using additional elevation data (e. g., DSM) for enhancing the performance of the semantic segmentation of aerial images.

Semantic Segmentation

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

6 code implementations NeurIPS 2020 Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang

Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.

Classification Dense Object Detection +1

CAST: A Correlation-based Adaptive Spectral Clustering Algorithm on Multi-scale Data

1 code implementation8 Jun 2020 Xiang Li, Ben Kao, Caihua Shan, Dawei Yin, Martin Ester

We study the problem of applying spectral clustering to cluster multi-scale data, which is data whose clusters are of various sizes and densities.

FGCRec: Fine-Grained Geographical Characteristics Modeling for Point-of-Interest Recommendation

1 code implementation IEEE International Conference on Communications 2020 Yijun Su, Xiang Li, Baoping Liu, Daren Zha, Ji Xiang, Wei Tang and Neng Gao.

With the popularity of location-based social networks (LBSNs), Point-of-Interest (POI) recommendation has become an essential location-based service to help people explore novel locations.

Recommendation Systems

Height estimation from single aerial images using a deep ordinal regression network

no code implementations4 Jun 2020 Xiang Li, Mingyang Wang, Yi Fang

Previous researches have extensively studied the problem of height estimation from aerial images based on stereo or multi-view image matching.

Change Detection

Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features

no code implementations CVPR 2020 Xiang Li, Yasushi Makihara, Chi Xu, Yasushi Yagi, Mingwu Ren

Existing gait recognition approaches typically focus on learning identity features that are invariant to covariates (e. g., the carrying status, clothing, walking speed, and viewing angle) and seldom involve learning features from the covariate aspect, which may lead to failure modes when variations due to the covariate overwhelm those due to the identity.

Disentanglement Gait Recognition

Convolutional Neural Network for Behavioral Modeling and Predistortion of Wideband Power Amplifiers

no code implementations20 May 2020 Xin Hu, Zhijun Liu, Xiaofei Yu, Yulong Zhao, WenHua Chen, Biao Hu, Xuekun Du, Xiang Li, Mohamed Helaoui, Weidong Wang, Fadhel M. Ghannouchi

We design a pre-designed filter using the convolutional layer to extract the basis functions required for the PA forward or reverse modeling.

One-Shot Object Detection without Fine-Tuning

1 code implementation8 May 2020 Xiang Li, Lin Zhang, Yau Pun Chen, Yu-Wing Tai, Chi-Keung Tang

Deep learning has revolutionized object detection thanks to large-scale datasets, but their object categories are still arguably very limited.

Metric Learning One-Shot Object Detection

A Concise yet Effective model for Non-Aligned Incomplete Multi-view and Missing Multi-label Learning

1 code implementation3 May 2020 Xiang Li, Songcan Chen

In aligning, we characterize the global and local structures of multiple labels to be high-rank and low-rank, respectively.

Model Selection Multi-Label Learning

Airborne LiDAR Point Cloud Classification with Graph Attention Convolution Neural Network

no code implementations20 Apr 2020 Congcong Wen, Xiang Li, Xiaojing Yao, Ling Peng, Tianhe Chi

To achieve point cloud classification, previous studies proposed point cloud deep learning models that can directly process raw point clouds based on PointNet-like architectures.

General Classification Graph Attention +2

TEDL: A Text Encryption Method Based on Deep Learning

1 code implementation9 Mar 2020 Xiang Li, Peng Wang

Firstly, both communication parties establish a word vector table by training a deep learning model according to specified hyperparameters.

Adversarial Multimodal Representation Learning for Click-Through Rate Prediction

no code implementations7 Mar 2020 Xiang Li, Chao Wang, Jiwei Tan, Xiaoyi Zeng, Dan Ou, Bo Zheng

Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations.

Click-Through Rate Prediction Representation Learning

Communication-Efficient Distributed SVD via Local Power Iterations

no code implementations19 Feb 2020 Xiang Li, Shusen Wang, Kun Chen, Zhihua Zhang

As a practical surrogate of OPT, sign-fixing, which uses a diagonal matrix with $\pm 1$ entries as weights, has better computation complexity and stability in experiments.

Distributed Computing

Representing Joint Hierarchies with Box Embeddings

1 code implementation AKBC 2020 Dhruvesh Patel, Shib Sankar Dasgupta, Michael Boratko, Xiang Li, Luke Vilnis, Andrew McCallum

Box Embeddings [Vilnis et al., 2018, Li et al., 2019] represent concepts with hyperrectangles in $n$-dimensional space and are shown to be capable of modeling tree-like structures efficiently by training on a large subset of the transitive closure of the WordNet hypernym graph.

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems

1 code implementation ACL 2020 Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang

We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.

Task-Oriented Dialogue Systems

Time-constrained Adaptive Influence Maximization

no code implementations6 Jan 2020 Guangmo Tong, Ruiqi Wang, Chen Ling, Zheng Dong, Xiang Li

The well-known influence maximization problem aims at maximizing the influence of one information cascade in a social network by selecting appropriate seed users prior to the diffusion process.

Social and Information Networks

Safe Sample Screening for Robust Support Vector Machine

no code implementations24 Dec 2019 Zhou Zhai, Bin Gu, Xiang Li, Heng Huang

To address this challenge, in this paper, we propose two safe sample screening rules for RSVM based on the framework of concave-convex procedure (CCCP).

Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration

1 code implementation NeurIPS 2019 Jianchun Chen, Lingjing Wang, Xiang Li, Yi Fang

To address this issue, we present an end-to-end trainable deep neural networks, named Arbitrary Continuous Geometric Transformation Networks (Arbicon-Net), to directly predict the dense displacement field for pairwise image alignment.

Image Registration

Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials

no code implementations12 Nov 2019 Yabo Dan, Yong Zhao, Xiang Li, Shaobo Li, Ming Hu, Jianjun Hu

The percentage of chemically valid (charge neutral and electronegativity balanced) samples out of all generated ones reaches 84. 5% by our GAN when trained with materials from ICSD even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules.

A General Early-Stopping Module for Crowdsourced Ranking

no code implementations4 Nov 2019 Caihua Shan, Leong Hou U, Nikos Mamoulis, Reynold Cheng, Xiang Li

The number of microtasks depends on the budget allocated for the problem.

An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms

no code implementations4 Nov 2019 Caihua Shan, Nikos Mamoulis, Reynold Cheng, Guoliang Li, Xiang Li, Yuqiu Qian

In this paper, we propose a Deep Reinforcement Learning (RL) framework for task arrangement, which is a critical problem for the success of crowdsourcing platforms.

Prediction stability as a criterion in active learning

no code implementations27 Oct 2019 Junyu Liu, Xiang Li, Jin Wang, Jiqiang Zhou, Jianxiong Shen

Recent breakthroughs made by deep learning rely heavily on large number of annotated samples.

Active Learning

Communication-Efficient Local Decentralized SGD Methods

no code implementations21 Oct 2019 Xiang Li, Wenhao Yang, Shusen Wang, Zhihua Zhang

Recently, the technique of local updates is a powerful tool in centralized settings to improve communication efficiency via periodical communication.

Distributed Computing

Density-Aware Convolutional Networks with Context Encoding for Airborne LiDAR Point Cloud Classification

no code implementations14 Oct 2019 Xiang Li, Mingyang Wang, Congcong Wen, Lingjing Wang, Nan Zhou, Yi Fang

Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.

3D Point Cloud Classification General Classification +1

Multi-label Detection and Classification of Red Blood Cells in Microscopic Images

no code implementations7 Oct 2019 Wei Qiu, Jiaming Guo, Xiang Li, Mengjia Xu, Mo Zhang, Ning Guo, Quanzheng Li

As the six networks are trained with image patches consisting of both individual cells and touching/overlapping cells, they can effectively recognize cell types that are presented in multi-instance image samples.

Classification General Classification +1

Improving One-shot NAS by Suppressing the Posterior Fading

no code implementations CVPR 2020 Xiang Li, Chen Lin, Chuming Li, Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang

In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights.

Neural Architecture Search Object Detection +1

Predicting Alzheimer's Disease by Hierarchical Graph Convolution from Positron Emission Tomography Imaging

no code implementations1 Oct 2019 Jiaming Guo, Wei Qiu, Xiang Li, Xuandong Zhao, Ning Guo, Quanzheng Li

Imaging-based early diagnosis of Alzheimer Disease (AD) has become an effective approach, especially by using nuclear medicine imaging techniques such as Positron Emission Topography (PET).

Graph Clustering

Invasiveness Prediction of Pulmonary Adenocarcinomas Using Deep Feature Fusion Networks

no code implementations21 Sep 2019 Xiang Li, Jiechao Ma, Hongwei Li

In this study, we explore the fusion of the two kinds of features and claim that radiomics features can be complementary to deep-learning features.

Computed Tomography (CT)

Directionally Constrained Fully Convolutional Neural Network For Airborne Lidar Point Cloud Classification

1 code implementation19 Aug 2019 Congcong Wen, Lina Yang, Ling Peng, Xiang Li, Tianhe Chi

In this paper, we proposed a directionally constrained fully convolutional neural network (D-FCN) that can take the original 3D coordinates and LiDAR intensity as input; thus, it can directly apply to unstructured 3D point clouds for semantic labeling.

General Classification Line Detection +1

Neural Image Compression and Explanation

1 code implementation9 Aug 2019 Xiang Li, Shihao Ji

Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network bandwidth is limited.

General Classification Image Classification +2

Quadruply Stochastic Gradients for Large Scale Nonlinear Semi-Supervised AUC Optimization

no code implementations29 Jul 2019 Wanli Shi, Bin Gu, Xiang Li, Xiang Geng, Heng Huang

To address this problem, in this paper, we propose a novel scalable quadruply stochastic gradient algorithm (QSG-S2AUC) for nonlinear semi-supervised AUC optimization.

Stochastic Optimization

Scalable Semi-Supervised SVM via Triply Stochastic Gradients

no code implementations26 Jul 2019 Xiang Geng, Bin Gu, Xiang Li, Wanli Shi, Guansheng Zheng, Heng Huang

Specifically, to handle two types of data instances involved in S$^3$VM, TSGS$^3$VM samples a labeled instance and an unlabeled instance as well with the random features in each iteration to compute a triply stochastic gradient.

ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning

no code implementations7 Jul 2019 Mo Zhang, Jie Zhao, Xiang Li, Li Zhang, Quanzheng Li

Such pixel-level dilation rates produce optimal receptive fields so that the information of objects with different sizes can be extracted at the corresponding scale.

Semantic Segmentation

On the Convergence of FedAvg on Non-IID Data

2 code implementations ICLR 2020 Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, Zhihua Zhang

In this paper, we analyze the convergence of \texttt{FedAvg} on non-iid data and establish a convergence rate of $\mathcal{O}(\frac{1}{T})$ for strongly convex and smooth problems, where $T$ is the number of SGDs.

Edge-computing Federated Learning

Cross-view Relation Networks for Mammogram Mass Detection

no code implementations1 Jul 2019 Jiechao Ma, Sen Liang, Xiang Li, Hongwei Li, Bjoern H. Menze, Rongguo Zhang, Wei-Shi Zheng

Mammogram is the most effective imaging modality for the mass lesion detection of breast cancer at the early stage.

Lesion Detection

Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registration

3 code implementations7 Jun 2019 Lingjing Wang, Xiang Li, Jianchun Chen, Yi Fang

In contrast to previous efforts (e. g. coherent point drift), CPD-Net can learn displacement field function to estimate geometric transformation from a training dataset, consequently, to predict the desired geometric transformation for the alignment of previously unseen pairs without any additional iterative optimization process.

Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks

no code implementations30 May 2019 Xiang Li, Chan Lu, Danni Cheng, Wei-Hong Li, Mei Cao, Bo Liu, Jiechao Ma, Wei-Shi Zheng

Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential.

Image-to-Image Translation

Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks

2 code implementations23 May 2019 Xiang Li, Xiaolin Hu, Jian Yang

The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features.

Image Classification Object Detection

Smoothing the Geometry of Probabilistic Box Embeddings

no code implementations ICLR 2019 Xiang Li, Luke Vilnis, Dongxu Zhang, Michael Boratko, Andrew McCallum

However, the hard edges of the boxes present difficulties for standard gradient based optimization; that work employed a special surrogate function for the disjoint case, but we find this method to be fragile.

ConvLab: Multi-Domain End-to-End Dialog System Platform

1 code implementation ACL 2019 Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao

We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments.

Inpatient2Vec: Medical Representation Learning for Inpatients

no code implementations18 Apr 2019 Ying Wang, Xiao Xu, Tao Jin, Xiang Li, Guotong Xie, Jian-Min Wang

In addition, for unordered medical activity set, existing medical RL methods utilize a simple pooling strategy, which would result in indistinguishable contributions among the activities for learning.

Representation Learning Semantic Similarity +1

Non-Rigid Point Set Registration Networks

1 code implementation2 Apr 2019 Lingjing Wang, Jianchun Chen, Xiang Li, Yi Fang

In contrast, the proposed point registration neural network (PR-Net) actively learns the registration pattern as a parametric function from a training dataset, consequently predict the desired geometric transformation to align a pair of point sets.

Shape Robust Text Detection with Progressive Scale Expansion Network

13 code implementations CVPR 2019 Wenhai Wang, Enze Xie, Xiang Li, Wenbo Hou, Tong Lu, Gang Yu, Shuai Shao

Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances.

Optical Character Recognition Scene Text Detection

Selective Kernel Networks

12 code implementations CVPR 2019 Xiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang

A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches.

Image Classification

A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning

no code implementations NeurIPS 2019 Xiang Li, Wenhao Yang, Zhihua Zhang

We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term.

reinforcement-learning

Dynamic Feature Fusion for Semantic Edge Detection

1 code implementation25 Feb 2019 Yuan Hu, Yunpeng Chen, Xiang Li, Jiashi Feng

In this work, we propose a novel dynamic feature fusion strategy that assigns different fusion weights for different input images and locations adaptively.

Edge Detection

Joint Optimization of Tree-based Index and Deep Model for Recommender Systems

1 code implementation NeurIPS 2019 Han Zhu, Daqing Chang, Ziru Xu, Pengye Zhang, Xiang Li, Jie He, Han Li, Jian Xu, Kun Gai

The previous work Tree-based Deep Model (TDM) \cite{zhu2018learning} greatly improves recommendation accuracy using tree index.

Recommendation Systems

Do Subsampled Newton Methods Work for High-Dimensional Data?

no code implementations13 Feb 2019 Xiang Li, Shusen Wang, Zhihua Zhang

Subsampled Newton methods approximate Hessian matrices through subsampling techniques, alleviating the cost of forming Hessian matrices but using sufficient curvature information.

Distributed Optimization

Group-Attention Single-Shot Detector (GA-SSD): Finding Pulmonary Nodules in Large-Scale CT Images

no code implementations18 Dec 2018 Jiechao Ma, Xiang Li, Hongwei Li, Bjoern H. Menze, Sen Liang, Rongguo Zhang, Wei-Shi Zheng

In this paper, we propose a novel and effective abnormality detector implementing the attention mechanism and group convolution on 3D single-shot detector (SSD) called group-attention SSD (GA-SSD).

Computed Tomography (CT) Finding Pulmonary Nodules In Large-Scale Ct Images

Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks

1 code implementation17 Dec 2018 Xiang Li, Shihao Ji

The proposed method is generic and can defend white-box and black-box attacks without the need of retraining the original CNN classifiers, and can further strengthen the defense by retraining CNN or end-to-end finetuning the whole pipeline.

Automated Segmentation of Cervical Nuclei in Pap Smear Images using Deformable Multi-path Ensemble Model

1 code implementation3 Dec 2018 Jie Zhao, Quanzheng Li, Xiang Li, Hongfeng Li, Li Zhang

Pap smear testing has been widely used for detecting cervical cancers based on the morphology properties of cell nuclei in microscopic image.

Medical Image Segmentation Semantic Segmentation

Improving the Robustness of Speech Translation

no code implementations2 Nov 2018 Xiang Li, Haiyang Xue, Wei Chen, Yang Liu, Yang Feng, Qun Liu

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source.

Automatic Speech Recognition Machine Translation +1

Community Detection with Graph Neural Networks

2 code implementations ICLR 2018 Zhengdao Chen, Xiang Li, Joan Bruna

This graph inference task can be recast as a node-wise graph classification problem, and, as such, computational detection thresholds can be translated in terms of learning within appropriate models.

Community Detection Graph Classification +1

Deep Diabetologist: Learning to Prescribe Hyperglycemia Medications with Hierarchical Recurrent Neural Networks

no code implementations17 Oct 2018 Jing Mei, Shiwan Zhao, Feng Jin, Eryu Xia, Haifeng Liu, Xiang Li

In healthcare, applying deep learning models to electronic health records (EHRs) has drawn considerable attention.

Time Series

Triple Attention Mixed Link Network for Single Image Super Resolution

no code implementations8 Oct 2018 Xi Cheng, Xiang Li, Jian Yang

Single image super resolution is of great importance as a low-level computer vision task.

Image Super-Resolution

Network Modeling and Pathway Inference from Incomplete Data ("PathInf")

no code implementations1 Oct 2018 Xiang Li, Qitian Chen, Xing Wang, Ning Guo, Nan Wu, Quanzheng Li

In this work, we developed a network inference method from incomplete data ("PathInf") , as massive and non-uniformly distributed missing values is a common challenge in practical problems.

Data Summarization

Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation

no code implementations ECCV 2018 Zhen-Yu Zhang, Zhen Cui, Chunyan Xu, Zequn Jie, Xiang Li, Jian Yang

In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks.

Monocular Depth Estimation Semantic Segmentation

Multi-Estimator Full Left Ventricle Quantification through Ensemble Learning

no code implementations6 Aug 2018 Jiasha Liu, Xiang Li, Hui Ren, Quanzheng Li

The framework combines two 1st-level modules: direct estimation module and a segmentation module.

Ensemble Learning

Adversarial Open-World Person Re-Identification

no code implementations ECCV 2018 Xiang Li, An-Cong Wu, Wei-Shi Zheng

The main idea is learning to attack feature extractor on the target people by using GAN to generate very target-like images (imposters), and in the meantime the model will make the feature extractor learn to tolerate the attack by discriminative learning so as to realize group-based verification.

Person Re-Identification

Shape Robust Text Detection with Progressive Scale Expansion Network

10 code implementations7 Jun 2018 Xiang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, Jian Yang

To address these problems, we propose a novel Progressive Scale Expansion Network (PSENet), designed as a segmentation-based detector with multiple predictions for each text instance.

Curved Text Detection

Modeling 4D fMRI Data via Spatio-Temporal Convolutional Neural Networks (ST-CNN)

no code implementations31 May 2018 Yu Zhao, Xiang Li, Wei zhang, Shijie Zhao, Milad Makkie, Mo Zhang, Quanzheng Li, Tianming Liu

Simultaneous modeling of the spatio-temporal variation patterns of brain functional network from 4D fMRI data has been an important yet challenging problem for the field of cognitive neuroscience and medical image analysis.

Brain Decoding

Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks

no code implementations28 May 2018 Yabo Ni, Dan Ou, Shichen Liu, Xiang Li, Wenwu Ou, An-Xiang Zeng, Luo Si

In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization.

Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures

no code implementations ACL 2018 Luke Vilnis, Xiang Li, Shikhar Murty, Andrew McCallum

Embedding methods which enforce a partial order or lattice structure over the concept space, such as Order Embeddings (OE) (Vendrov et al., 2016), are a natural way to model transitive relational data (e. g. entailment graphs).

Knowledge Graphs

Pelee: A Real-Time Object Detection System on Mobile Devices

7 code implementations NeurIPS 2018 Robert J. Wang, Xiang Li, Charles X. Ling

In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead.

Real-Time Object Detection

Adversarial Metric Learning

no code implementations9 Feb 2018 Shuo Chen, Chen Gong, Jian Yang, Xiang Li, Yang Wei, Jun Li

In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs.

Metric Learning

Mixed Link Networks

1 code implementation6 Feb 2018 Wenhai Wang, Xiang Li, Jian Yang, Tong Lu

Basing on the analysis by revealing the equivalence of modern networks, we find that both ResNet and DenseNet are essentially derived from the same "dense topology", yet they only differ in the form of connection -- addition (dubbed "inner link") vs. concatenation (dubbed "outer link").

Representation Learning

Densely Connected Bidirectional LSTM with Applications to Sentence Classification

2 code implementations3 Feb 2018 Zixiang Ding, Rui Xia, Jianfei Yu, Xiang Li, Jian Yang

Deep neural networks have recently been shown to achieve highly competitive performance in many computer vision tasks due to their abilities of exploring in a much larger hypothesis space.

Classification General Classification +1

SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks

1 code implementation31 Jan 2018 Xi Cheng, Xiang Li, Ying Tai, Jian Yang

Single image super resolution is a very important computer vision task, with a wide range of applications.