Search Results for author: Ang Li

Found 167 papers, 36 papers with code

A Challenge Dataset and Effective Models for Conversational Stance Detection

no code implementations17 Mar 2024 Fuqiang Niu, Min Yang, Ang Li, Baoquan Zhang, Xiaojiang Peng, BoWen Zhang

Previous stance detection studies typically concentrate on evaluating stances within individual instances, thereby exhibiting limitations in effectively modeling multi-party discussions concerning the same specific topic, as naturally transpire in authentic social media interactions.

Accurate and Data-Efficient Micro-XRD Phase Identification Using Multi-Task Learning: Application to Hydrothermal Fluids

no code implementations15 Mar 2024 Yanfei Li, Juejing Liu, Xiaodong Zhao, Wenjun Liu, Tong Geng, Ang Li, Xin Zhang

Traditional analysis of highly distorted micro-X-ray diffraction ({\mu}-XRD) patterns from hydrothermal fluid environments is a time-consuming process, often requiring substantial data preprocessing and labeled experimental data.

Binary Classification Multi-Task Learning

HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback

no code implementations13 Mar 2024 Ang Li, Qiugen Xiao, Peng Cao, Jian Tang, Yi Yuan, Zijie Zhao, Xiaoyuan Chen, Liang Zhang, Xiangyang Li, Kaitong Yang, Weidong Guo, Yukang Gan, Xu Yu, Daniell Wang, Ying Shan

Using ChatGPT as a labeler to provide feedback on open-domain prompts in RLAIF training, we observe an increase in human evaluators' preference win ratio for model responses, but a decrease in evaluators' satisfaction rate.

Language Modelling Large Language Model +2

Enhancing Court View Generation with Knowledge Injection and Guidance

1 code implementation7 Mar 2024 Ang Li, Yiquan Wu, Yifei Liu, Fei Wu, Ming Cai, Kun Kuang

Court View Generation (CVG) is a challenging task in the field of Legal Artificial Intelligence (LegalAI), which aims to generate court views based on the plaintiff claims and the fact descriptions.

Text Generation

From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction

1 code implementation7 Mar 2024 Ang Li, Qiangchao Chen, Yiquan Wu, Ming Cai, Xiang Zhou, Fei Wu, Kun Kuang

In this paper, we introduce a novel From Graph to Word Bag (FWGB) approach, which introduces domain knowledge regarding constituent elements to guide the model in making judgments on confusing charges, much like a judge's reasoning process.

A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity

no code implementations23 Feb 2024 Ryan L'Abbate, Anthony D'Onofrio Jr., Samuel Stein, Samuel Yen-Chi Chen, Ang Li, Pin-Yu Chen, Juntao Chen, Ying Mao

In this study, we concentrate on quantum deep learning and introduce a collaborative classical-quantum architecture called co-TenQu.

Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting

1 code implementation23 Feb 2024 Rong Dai, Yonggang Zhang, Ang Li, Tongliang Liu, Xun Yang, Bo Han

These hard samples are then employed to promote the quality of the ensemble model by adjusting the ensembling weights for each client model.

Federated Learning

Multi-modal Stance Detection: New Datasets and Model

no code implementations22 Feb 2024 Bin Liang, Ang Li, Jingqian Zhao, Lin Gui, Min Yang, Yue Yu, Kam-Fai Wong, Ruifeng Xu

Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets.

Stance Detection

Time-Transformer: Integrating Local and Global Features for Better Time Series Generation

1 code implementation18 Dec 2023 Yuansan Liu, Sudanthi Wijewickrema, Ang Li, Christofer Bester, Stephen O'Leary, James Bailey

Experimental results demonstrate that our model can outperform existing state-of-the-art models in 5 out of 6 datasets, specifically on those with data containing both global and local properties.

Data Augmentation Time Series +1

Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs

no code implementations8 Nov 2023 Hongwu Peng, Caiwen Ding, Tong Geng, Sutanay Choudhury, Kevin Barker, Ang Li

The relentless advancement of artificial intelligence (AI) and machine learning (ML) applications necessitates the development of specialized hardware accelerators capable of handling the increasing complexity and computational demands.

Research Team Identification Based on Representation Learning of Academic Heterogeneous Information Network

no code implementations2 Nov 2023 Junfu Wang, Yawen Li, Zhe Xue, Ang Li

Academic networks in the real world can usually be described by heterogeneous information networks composed of multi-type nodes and relationships.

Representation Learning

Federated Topic Model and Model Pruning Based on Variational Autoencoder

no code implementations1 Nov 2023 Chengjie Ma, Yawen Li, Meiyu Liang, Ang Li

The first method involves slow pruning throughout the entire model training process, which has limited acceleration effect on the model training process, but can ensure that the pruned model achieves higher accuracy.

Adversarial Examples Are Not Real Features

1 code implementation NeurIPS 2023 Ang Li, Yifei Wang, Yiwen Guo, Yisen Wang

A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract non-robust features from adversarial examples and these features alone are useful for classification.

Contrastive Learning Self-Supervised Learning

SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models

no code implementations29 Oct 2023 Zhixu Du, Shiyu Li, Yuhao Wu, Xiangyu Jiang, Jingwei Sun, Qilin Zheng, Yongkai Wu, Ang Li, Hai "Helen" Li, Yiran Chen

Specifically, SiDA attains a remarkable speedup in MoE inference with up to 3. 93X throughput increasing, up to 75% latency reduction, and up to 80% GPU memory saving with down to 1% performance drop.

Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data

1 code implementation8 Oct 2023 Zuxuan Wu, Zejia Weng, Wujian Peng, Xitong Yang, Ang Li, Larry S. Davis, Yu-Gang Jiang

Despite significant results achieved by Contrastive Language-Image Pretraining (CLIP) in zero-shot image recognition, limited effort has been made exploring its potential for zero-shot video recognition.

Action Recognition Continual Learning +5

Toward Intelligent Emergency Control for Large-scale Power Systems: Convergence of Learning, Physics, Computing and Control

no code implementations8 Oct 2023 Qiuhua Huang, Renke Huang, Tianzhixi Yin, Sohom Datta, Xueqing Sun, Jason Hou, Jie Tan, Wenhao Yu, YuAn Liu, Xinya Li, Bruce Palmer, Ang Li, Xinda Ke, Marianna Vaiman, Song Wang, Yousu Chen

Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56000 scenarios.

FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent

no code implementations4 Oct 2023 Ziyao Wang, Jianyu Wang, Ang Li

The theoretical landscape of federated learning (FL) undergoes rapid evolution, but its practical application encounters a series of intricate challenges, and hyperparameter optimization is one of these critical challenges.

Federated Learning Hyperparameter Optimization

Symbol-Level Precoding for MU-MIMO System with RIRC Receiver

no code implementations27 Jul 2023 Xiao Tong, Ang Li, Lei Lei, Fan Liu, Fuwang Dong

The problem is solved using the alternating optimization (AO) method, and the optimal solution structures for transmit precoding and receive combining matrices are derived by using Lagrangian and Karush-Kuhn-Tucker (KKT) conditions, based on which, the original problem is transformed into an equivalent quadratic programming problem, enabling more efficient solutions.

A Novel Spatial-Temporal Variational Quantum Circuit to Enable Deep Learning on NISQ Devices

no code implementations19 Jul 2023 Jinyang Li, Zhepeng Wang, Zhirui Hu, Prasanna Date, Ang Li, Weiwen Jiang

The results of the evaluation on the standard dataset for binary classification show that ST-VQC can achieve over 30% accuracy improvement compared with existing VQCs on actual quantum computers.

Binary Classification

Faster-Than-Nyquist Symbol-Level Precoding for Wideband Integrated Sensing and Communications

no code implementations26 Jun 2023 Zihan Liao, Fan Liu, Ang Li, Christos Masouros

In this paper, we present an innovative symbol-level precoding (SLP) approach for a wideband multi-user multi-input multi-output (MU-MIMO) downlink Integrated Sensing and Communications (ISAC) system employing faster-than-Nyquist (FTN) signaling.

BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUs

no code implementations4 May 2023 Jou-An Chen, Hsin-Hsuan Sung, Xipeng Shen, Sutanay Choudhury, Ang Li

It fills the gap by proposing a series of abstractions and techniques to map binary GNNs and their computations best to fit the nature of bit manipulations on GPUs.

Machine Learning Automated Approach for Enormous Synchrotron X-Ray Diffraction Data Interpretation

no code implementations20 Mar 2023 Xiaodong Zhao, YiXuan Luo, Juejing Liu, Wenjun Liu, Kevin M. Rosso, Xiaofeng Guo, Tong Geng, Ang Li, Xin Zhang

This study highlighted the importance of labeled experimental patterns on the training of DNN models to solve u-XRD mapping data from in-situ experiments involving liquid phase.

MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling

no code implementations16 Mar 2023 Xuzhe Zhang, Yuhao Wu, Elsa Angelini, Ang Li, Jia Guo, Jerod M. Rasmussen, Thomas G. O'Connor, Pathik D. Wadhwa, Andrea Parolin Jackowski, Hai Li, Jonathan Posner, Andrew F. Laine, Yun Wang

In this study, we introduce Masked Autoencoding and Pseudo-Labeling Segmentation (MAPSeg), a $\textbf{unified}$ UDA framework with great versatility and superior performance for heterogeneous and volumetric medical image segmentation.

Domain Generalization Image Segmentation +5

Deep Learning-Based Channel Extrapolation for Pattern Reconfigurable Massive MIMO

no code implementations8 Mar 2023 Mu Liang, Ang Li

In order to reduce the pilot overheads, we propose a new channel estimation method specially for PR-MIMO systems, which divides the transmit antennas of PR-MIMO into groups and antennas in different groups employ different radiation modes.

AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving

no code implementations17 Feb 2023 Tianyue Zheng, Ang Li, Zhe Chen, Hongbo Wang, Jun Luo

Object detection with on-board sensors (e. g., lidar, radar, and camera) play a crucial role in autonomous driving (AD), and these sensors complement each other in modalities.

Autonomous Driving Federated Learning +3

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization

1 code implementation1 Feb 2023 Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

Our framework extends CLIP with minimal modifications to model spatial-temporal relationships in videos, making it a specialized video classifier, while striving for generalization.

Action Recognition Continual Learning +2

Epsilon-Identifiability of Causal Quantities

no code implementations27 Jan 2023 Ang Li, Scott Mueller, Judea Pearl

Identifying the effects of causes and causes of effects is vital in virtually every scientific field.

counterfactual

Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume

no code implementations5 Jan 2023 Ang Li, Jiayi Han, Yongjian Zhao, Keyu Li, Li Liu

While the US is not a standard paradigm for spinal surgery, the scarcity of intra-operative clinical US data is an insurmountable bottleneck in training a neural network.

Segmentation

PolicyCleanse: Backdoor Detection and Mitigation for Competitive Reinforcement Learning

no code implementations ICCV 2023 Junfeng Guo, Ang Li, Lixu Wang, Cong Liu

To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in multi-agent RL systems, with the objective of detecting Trojan agents as well as the corresponding potential trigger actions, and further trying to mitigate their bad impact.

Machine Unlearning reinforcement-learning +1

More Generalized and Personalized Unsupervised Representation Learning In A Distributed System

no code implementations11 Nov 2022 Yuewei Yang, Jingwei Sun, Ang Li, Hai Li, Yiran Chen

In this work, we propose a novel method, FedStyle, to learn a more generalized global model by infusing local style information with local content information for contrastive learning, and to learn more personalized local models by inducing local style information for downstream tasks.

Contrastive Learning Federated Learning +1

Probabilities of Causation: Role of Observational Data

no code implementations17 Oct 2022 Ang Li, Judea Pearl

In this paper, we discuss the conditions that observational data are worth considering to improve the quality of the bounds.

Decision Making valid

Learning Probabilities of Causation from Finite Population Data

no code implementations16 Oct 2022 Ang Li, Song Jiang, Yizhou Sun, Judea Pearl

This paper deals with the problem of learning the probabilities of causation of subpopulations given finite population data.

Unit Selection: Learning Benefit Function from Finite Population Data

no code implementations15 Oct 2022 Ang Li, Song Jiang, Yizhou Sun, Judea Pearl

In this paper, we present a machine learning framework that uses the bounds of the benefit function that are estimable from the finite population data to learn the bounds of the benefit function for each cell of characteristics.

Cross-modal Search Method of Technology Video based on Adversarial Learning and Feature Fusion

no code implementations11 Oct 2022 Xiangbin Liu, Junping Du, Meiyu Liang, Ang Li

The proposed method uses the framework of adversarial learning to construct a video multimodal feature fusion network and a feature mapping network as generator, a modality discrimination network as discriminator.

Cross-Modal Retrieval Retrieval +1

QuCNN : A Quantum Convolutional Neural Network with Entanglement Based Backpropagation

no code implementations11 Oct 2022 Samuel A. Stein, Ying Mao, James Ang, Ang Li

Quantum Machine Learning continues to be a highly active area of interest within Quantum Computing.

Quantum Machine Learning

Probabilities of Causation: Adequate Size of Experimental and Observational Samples

no code implementations10 Oct 2022 Ang Li, Ruirui Mao, Judea Pearl

The assumption is that one is in possession of a large enough sample to permit an accurate estimation of the experimental and observational distributions.

Decision Making

Unit Selection: Case Study and Comparison with A/B Test Heuristic

no code implementations10 Oct 2022 Ang Li, Judea Pearl

The unit selection problem defined by Li and Pearl identifies individuals who have desired counterfactual behavior patterns, for example, individuals who would respond positively if encouraged and would not otherwise.

counterfactual

Rethinking Normalization Methods in Federated Learning

no code implementations7 Oct 2022 Zhixu Du, Jingwei Sun, Ang Li, Pin-Yu Chen, Jianyi Zhang, Hai "Helen" Li, Yiran Chen

We also show that layer normalization is a better choice in FL which can mitigate the external covariate shift and improve the performance of the global model.

Federated Learning

Scientific Paper Classification Based on Graph Neural Network with Hypergraph Self-attention Mechanism

no code implementations7 Oct 2022 Jiashun Liu, Zhe Xue, Ang Li

Then the whole heterogeneous information network is transformed into a hypergraph composed of different hyperedges.

Management

Embedding Representation of Academic Heterogeneous Information Networks Based on Federated Learning

no code implementations7 Oct 2022 Junfu Wang, Yawen Li, Meiyu Liang, Ang Li

To solve the above challenges, aiming at the data information of scientific research teams closely related to science and technology, we proposed an academic heterogeneous information network embedding representation learning method based on federated learning (FedAHE), which utilizes node attention and meta path attention mechanism to learn low-dimensional, dense and real-valued vector representations while preserving the rich topological information and meta-path-based semantic information of nodes in network.

Blocking Federated Learning +1

Scientific and Technological News Recommendation Based on Knowledge Graph with User Perception

no code implementations7 Oct 2022 Yuyao Zeng, Junping Du, Zhe Xue, Ang Li

KGUPN contains three main layers, which are the propagation representation layer, the contextual information layer and collaborative relation layer.

Collaborative Filtering News Recommendation +2

Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction

no code implementations30 Sep 2022 Jianyi Zhang, Ang Li, Minxue Tang, Jingwei Sun, Xiang Chen, Fan Zhang, Changyou Chen, Yiran Chen, Hai Li

Based on this measure, we also design a computation-efficient client sampling strategy, such that the actively selected clients will generate a more class-balanced grouped dataset with theoretical guarantees.

Federated Learning Privacy Preserving

MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms

1 code implementation14 Sep 2022 yuke wang, Boyuan Feng, Zheng Wang, Tong Geng, Kevin Barker, Ang Li, Yufei Ding

For irregularly sparse and fine-grained GNN workloads, such solutions miss the opportunity to jointly schedule/optimize the computation and communication operations for high-performance delivery.

Layout Design Management

Unit Selection with Nonbinary Treatment and Effect

no code implementations20 Aug 2022 Ang Li, Judea Pearl

We propose an algorithm to test the identifiability of the nonbinary benefit function and an algorithm to compute the bounds of the nonbinary benefit function using experimental and observational data.

Probabilities of Causation with Nonbinary Treatment and Effect

no code implementations19 Aug 2022 Ang Li, Judea Pearl

This paper deals with the problem of estimating the probabilities of causation when treatment and effect are not binary.

SphereFed: Hyperspherical Federated Learning

no code implementations19 Jul 2022 Xin Dong, Sai Qian Zhang, Ang Li, H. T. Kung

Federated Learning aims at training a global model from multiple decentralized devices (i. e. clients) without exchanging their private local data.

Federated Learning

A Synergistic Compilation Workflow for Tackling Crosstalk in Quantum Machines

no code implementations12 Jul 2022 Fei Hua, Yuwei Jin, Ang Li, Chenxu Liu, Meng Wang, Yanhao Chen, Chi Zhang, Ari Hayes, Samuel Stein, Minghao Guo, Yipeng Huang, Eddy Z. Zhang

Evaluations through simulation and on real IBM-Q devices show that our framework can significantly reduce the error rate by up to 6$\times$, with only $\sim$60\% circuit depth compared to state-of-the-art gate scheduling approaches.

Scheduling

Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTa

no code implementations6 Jul 2022 Tianyu Zhao, Junping Du, Zhe Xue, Ang Li, Zeli Guan

Aspect-Based Sentiment Analysis (ABSA) is a fine-grained task in the field of sentiment analysis, which aims to predict the polarity of aspects.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +4

A Rare Topic Discovery Model for Short Texts Based on Co-occurrence word Network

no code implementations30 Jun 2022 Chengjie Ma, Junping Du, Yingxia Shao, Ang Li, Zeli Guan

We provide a simple and general solution for the discovery of scarce topics in unbalanced short-text datasets, namely, a word co-occurrence network-based model CWIBTD, which can simultaneously address the sparsity and unbalance of short-text topics and attenuate the effect of occasional pairwise occurrences of words, allowing the model to focus more on the discovery of scarce topics.

Chinese Word Sense Embedding with SememeWSD and Synonym Set

2 code implementations29 Jun 2022 Yangxi Zhou, Junping Du, Zhe Xue, Ang Li, Zeli Guan

To address this limitation, we propose SememeWSD Synonym (SWSDS) model to assign a different vector to every sense of polysemous words with the help of word sense disambiguation (WSD) and synonym set in OpenHowNet.

Semantic Similarity Semantic Textual Similarity +1

H-GCN: A Graph Convolutional Network Accelerator on Versal ACAP Architecture

no code implementations28 Jun 2022 Chengming Zhang, Tong Geng, Anqi Guo, Jiannan Tian, Martin Herbordt, Ang Li, Dingwen Tao

Graph Neural Networks (GNNs) have drawn tremendous attention due to their unique capability to extend Machine Learning (ML) approaches to applications broadly-defined as having unstructured data, especially graphs.

BIG-bench Machine Learning

A sentiment analysis model for car review texts based on adversarial training and whole word mask BERT

no code implementations6 Jun 2022 Xingchen Liu, Yawen Li, Yingxia Shao, Ang Li, Jian Liang

Based on this, we propose a car review text sentiment analysis model based on adversarial training and whole word mask BERT(ATWWM-BERT).

Decision Making Sentiment Analysis

Searching Similarity Measure for Binarized Neural Networks

no code implementations5 Jun 2022 Yanfei Li, Ang Li, Huimin Yu

Being a promising model to be deployed in resource-limited devices, Binarized Neural Networks (BNNs) have drawn extensive attention from both academic and industry.

GAAF: Searching Activation Functions for Binary Neural Networks through Genetic Algorithm

1 code implementation5 Jun 2022 Yanfei Li, Tong Geng, Samuel Stein, Ang Li, Huimin Yu

To close the accuracy gap, in this paper we propose to add a complementary activation function (AF) ahead of the sign based binarization, and rely on the genetic algorithm (GA) to automatically search for the ideal AFs.

Binarization

Sentiment Analysis of Online Travel Reviews Based on Capsule Network and Sentiment Lexicon

no code implementations5 Jun 2022 Jia Wang, Junping Du, Yingxia Shao, Ang Li

In this paper, we study the text sentiment classification of online travel reviews based on social media online comments and propose the SCCL model based on capsule network and sentiment lexicon.

Language Modelling Sentiment Analysis +1

Bi-convolution matrix factorization algorithm based on improved ConvMF

no code implementations2 Jun 2022 Peiyu Liu, Junping Du, Zhe Xue, Ang Li

With the rapid development of information technology, "information overload" has become the main theme that plagues people's online life.

Towards Model Generalization for Monocular 3D Object Detection

no code implementations23 May 2022 Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, Junjun Jiang

However, caused by severe domain gaps (e. g., the field of view (FOV), pixel size, and object size among datasets), Mono3D detectors have difficulty in generalization, leading to drastic performance degradation on unseen domains.

Autonomous Driving Monocular 3D Object Detection +3

Iterative Geometry-Aware Cross Guidance Network for Stereo Image Inpainting

no code implementations8 May 2022 Ang Li, Shanshan Zhao, Qingjie Zhang, Qiuhong Ke

The IGGNet contains two key ingredients, i. e., a Geometry-Aware Attention (GAA) module and an Iterative Cross Guidance (ICG) strategy.

Image Inpainting

Cross-media Scientific Research Achievements Query based on Ranking Learning

no code implementations26 Apr 2022 Benzhi Wang, Meiyu Liang, Ang Li

With the advent of the information age, the scale of data on the Internet is getting larger and larger, and it is full of text, images, videos, and other information.

Decision Making

Profiling and Evolution of Intellectual Property

no code implementations20 Apr 2022 Bowen Yu, Yingxia Shao, Ang Li

In recent years, with the rapid growth of Internet data, the number and types of scientific and technological resources are also rapidly expanding.

Retrieval

Research on Intellectual Property Resource Profile and Evolution Law

no code implementations13 Apr 2022 Yuhui Wang, Yingxia Shao, Ang Li

In the era of big data, intellectual property-oriented scientific and technological resources show the trend of large data scale, high information density and low value density, which brings severe challenges to the effective use of intellectual property resources, and the demand for mining hidden information in intellectual property is increasing.

Retrieval of Scientific and Technological Resources for Experts and Scholars

no code implementations13 Apr 2022 Suyu Ouyang, Yingxia Shao, Ang Li

The scientific and technological resources of experts and scholars are mainly composed of basic attributes and scientific research achievements.

Relation Extraction Representation Learning +1

Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academic Conferences

no code implementations11 Apr 2022 Runyu Yu, Zhe Xue, Ang Li

In recent years, with the continuous progress of science and technology, the number of scientific research achievements is increasing day by day, as the exchange platform and medium of scientific research achievements, the scientific and technological academic conferences have become more and more abundant.

Accurate Portraits of Scientific Resources and Knowledge Service Components

no code implementations11 Apr 2022 Yue Wang, Zhe Xue, Ang Li

With the advent of the cloud computing era, the cost of creating, capturing and managing information has gradually decreased.

Cloud Computing Management

Research on Cross-media Science and Technology Information Data Retrieval

no code implementations11 Apr 2022 Yang Jiang, Zhe Xue, Ang Li

Since the era of big data, the Internet has been flooded with all kinds of information.

Information Retrieval Retrieval

Information-theoretic Online Memory Selection for Continual Learning

no code implementations ICLR 2022 Shengyang Sun, Daniele Calandriello, Huiyi Hu, Ang Li, Michalis Titsias

A challenging problem in task-free continual learning is the online selection of a representative replay memory from data streams.

Continual Learning

FastMapSVM: Classifying Complex Objects Using the FastMap Algorithm and Support-Vector Machines

1 code implementation7 Apr 2022 Malcolm C. A. White, Kushal Sharma, Ang Li, T. K. Satish Kumar, Nori Nakata

In this paper, we advance FastMapSVM -- an interpretable Machine Learning framework for classifying complex objects -- as an advantageous alternative to Neural Networks for general classification tasks.

General Classification Interpretable Machine Learning

Towards Collaborative Intelligence: Routability Estimation based on Decentralized Private Data

no code implementations30 Mar 2022 Jingyu Pan, Chen-Chia Chang, Zhiyao Xie, Ang Li, Minxue Tang, Tunhou Zhang, Jiang Hu, Yiran Chen

To further strengthen the results, we co-design a customized ML model FLNet and its personalization under the decentralized training scenario.

Federated Learning

Research Scholar Interest Mining Method based on Load Centrality

no code implementations21 Mar 2022 Yang Jiang, Zhe Xue, Ang Li

In the era of big data, it is possible to carry out cooperative research on the research results of researchers through papers, patents and other data, so as to study the role of researchers, and produce results in the analysis of results.

Academic Resource Text Level Multi-label Classification based on Attention

no code implementations21 Mar 2022 Yue Wang, Yawen Li, Ang Li

We propose an attention-based hierarchical multi-label classification algorithm of academic texts (AHMCA) by integrating features such as text, keywords, and hierarchical structure, the academic documents are classified into the most relevant categories.

Document Embedding Hierarchical Multi-label Classification +2

Semantic Similarity Computing for Scientific Academic Conferences fused with domain features

no code implementations21 Mar 2022 Runyu Yu, Yawen Li, Ang Li

Aiming at the problem that the current general-purpose semantic text similarity calculation methods are difficult to use the semantic information of scientific academic conference data, a semantic similarity calculation algorithm for scientific academic conferences by fusion with domain features is proposed.

Keyword Extraction Semantic Similarity +2

Scientific and Technological Information Oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval

no code implementations16 Mar 2022 Ang Li, Junping Du, Feifei Kou, Zhe Xue, Xin Xu, Mingying Xu, Yang Jiang

In light of this, we propose a scientific and technological information oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval method (SMCR) to find an effective common subspace.

Information Retrieval Retrieval +2

Topological EEG Nonlinear Dynamics Analysis for Emotion Recognition

no code implementations14 Mar 2022 Yan Yan, Xuankun Wu, Chengdong Li, Yini He, Zhicheng Zhang, Huihui Li, Ang Li, Lei Wang

The proposed work is the first investigation in the emotion recognition oriented EEG topological feature analysis, which brought a novel insight into the brain neural system nonlinear dynamics analysis and feature extraction.

Arousal Estimation Dominance Estimation +7

I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization

no code implementations7 Mar 2022 Tong Geng, Chunshu Wu, Yongan Zhang, Cheng Tan, Chenhao Xie, Haoran You, Martin C. Herbordt, Yingyan Lin, Ang Li

In this paper we propose a novel hardware accelerator for GCN inference, called I-GCN, that significantly improves data locality and reduces unnecessary computation.

PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning

no code implementations8 Feb 2022 Junfeng Guo, Ang Li, Cong Liu

To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in a multi-agent competitive reinforcement learning system, with the objective of detecting Trojan agents as well as the corresponding potential trigger actions, and further trying to mitigate their Trojan behavior.

Machine Unlearning reinforcement-learning +1

M2DGR: A Multi-sensor and Multi-scenario SLAM Dataset for Ground Robots

2 code implementations19 Dec 2021 Jie Yin, Ang Li, Tao Li, Wenxian Yu, Danping Zou

We introduce M2DGR: a novel large-scale dataset collected by a ground robot with a full sensor-suite including six fish-eye and one sky-pointing RGB cameras, an infrared camera, an event camera, a Visual-Inertial Sensor (VI-sensor), an inertial measurement unit (IMU), a LiDAR, a consumer-grade Global Navigation Satellite System (GNSS) receiver and a GNSS-IMU navigation system with real-time kinematic (RTK) signals.

SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations

1 code implementation9 Dec 2021 Zhenyu Li, Zehui Chen, Ang Li, Liangji Fang, Qinhong Jiang, Xianming Liu, Junjun Jiang, Bolei Zhou, Hang Zhao

To bridge this gap, we aim to learn a spatial-aware visual representation that can describe the three-dimensional space and is more suitable and effective for these tasks.

Contrastive Learning Unsupervised Pre-training

Semi-Supervised Vision Transformers

1 code implementation22 Nov 2021 Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang

Surprisingly, we show Vision Transformers perform significantly worse than Convolutional Neural Networks when only a small set of labeled data is available.

Inductive Bias Semi-Supervised Image Classification

One Pass ImageNet

no code implementations NeurIPS Workshop ImageNet_PPF 2021 Huiyi Hu, Ang Li, Daniele Calandriello, Dilan Gorur

We present the One Pass ImageNet (OPIN) problem, which aims to study the effectiveness of deep learning in a streaming setting.

Continual Learning

AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis

1 code implementation ICLR 2022 Junfeng Guo, Ang Li, Cong Liu

We approach this problem from the optimization perspective and show that the objective of backdoor detection is bounded by an adversarial objective.

G-CoS: GNN-Accelerator Co-Search Towards Both Better Accuracy and Efficiency

no code implementations18 Sep 2021 Yongan Zhang, Haoran You, Yonggan Fu, Tong Geng, Ang Li, Yingyan Lin

While end-to-end jointly optimizing GNNs and their accelerators is promising in boosting GNNs' inference efficiency and expediting the design process, it is still underexplored due to the vast and distinct design spaces of GNNs and their accelerators.

Unit Selection with Causal Diagram

no code implementations15 Sep 2021 Ang Li, Judea Pearl

The unit selection problem aims to identify a set of individuals who are most likely to exhibit a desired mode of behavior, for example, selecting individuals who would respond one way if encouraged and a different way if not encouraged.

ETA Prediction with Graph Neural Networks in Google Maps

no code implementations25 Aug 2021 Austin Derrow-Pinion, Jennifer She, David Wong, Oliver Lange, Todd Hester, Luis Perez, Marc Nunkesser, Seongjae Lee, Xueying Guo, Brett Wiltshire, Peter W. Battaglia, Vishal Gupta, Ang Li, Zhongwen Xu, Alvaro Sanchez-Gonzalez, Yujia Li, Petar Veličković

Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike.

Graph Representation Learning

Binary Complex Neural Network Acceleration on FPGA

no code implementations10 Aug 2021 Hongwu Peng, Shanglin Zhou, Scott Weitze, Jiaxin Li, Sahidul Islam, Tong Geng, Ang Li, Wei zhang, Minghu Song, Mimi Xie, Hang Liu, Caiwen Ding

Deep complex networks (DCN), in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision-making requirements of many deployable systems dealing with short observations or short signal bursts.

Decision Making

Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective

no code implementations3 Jul 2021 Binghui Wang, Jiayi Guo, Ang Li, Yiran Chen, Hai Li

Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification, link prediction, etc.

Link Prediction Node Classification +2

Task-agnostic Continual Learning with Hybrid Probabilistic Models

no code implementations ICML Workshop INNF 2021 Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu

Learning new tasks continuously without forgetting on a constantly changing data distribution is essential for real-world problems but extremely challenging for modern deep learning.

Anomaly Detection Continual Learning +1

APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores

1 code implementation23 Jun 2021 Boyuan Feng, yuke wang, Tong Geng, Ang Li, Yufei Ding

Over the years, accelerating neural networks with quantization has been widely studied.

Quantization

Bounds on Causal Effects and Application to High Dimensional Data

no code implementations23 Jun 2021 Ang Li, Judea Pearl

This paper addresses the problem of estimating causal effects when adjustment variables in the back-door or front-door criterion are partially observed.

Dimensionality Reduction Vocal Bursts Intensity Prediction

Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective

1 code implementation CVPR 2021 Jingwei Sun, Ang Li, Binghui Wang, Huanrui Yang, Hai Li, Yiran Chen

The key idea of our defense is learning to perturb data representation such that the quality of the reconstructed data is severely degraded, while FL performance is maintained.

Federated Learning Inference Attack

Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting

no code implementations3 Jun 2021 Ang Li, Qiuhong Ke, Xingjun Ma, Haiqin Weng, Zhiyuan Zong, Feng Xue, Rui Zhang

A promising countermeasure against such forgeries is deep inpainting detection, which aims to locate the inpainted regions in an image.

Image Inpainting

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

no code implementations CVPR 2022 Xin Dong, Junfeng Guo, Ang Li, Wei-Te Ting, Cong Liu, H. T. Kung

Based upon this observation, we propose a novel metric called Neural Mean Discrepancy (NMD), which compares neural means of the input examples and training data.

General Classification Out-of-Distribution Detection +1

BCNN: Binary Complex Neural Network

no code implementations28 Mar 2021 Yanfei Li, Tong Geng, Ang Li, Huimin Yu

Motivated by the complex neural networks, in this paper we introduce complex representation into the BNNs and propose Binary complex neural network -- a novel network design that processes binary complex inputs and weights through complex convolution, but still can harvest the extraordinary computation efficiency of BNNs.

Fluid forces and vortex patterns of an oscillating cylinder pair in still water with both side-by-side and tandem configurations

no code implementations10 Mar 2021 Ang Li, Shengmin Shi, Dixia Fan

In order to reveal the detailed flow physics that result in significant fluid forces alternations, the detailed flow visualization is provided by the numerical simulation: the small gap between two cylinders in a side-by-side configuration will result in a strong gap jet that enhances the energy dissipation and increase the drag, while due to the flow blocking effect for two cylinders in a tandem configuration, the drag coefficient decreases.

Fluid Dynamics

PredCoin: Defense against Query-based Hard-label Attack

no code implementations4 Feb 2021 Junfeng Guo, Yaswanth Yadlapalli, Thiele Lothar, Ang Li, Cong Liu

PredCoin poisons the gradient estimation step, an essential component of most QBHL attacks.

Hard-label Attack

Cramér-Rao Bound Optimization for Joint Radar-Communication Design

no code implementations29 Jan 2021 Fan Liu, Ya-Feng Liu, Ang Li, Christos Masouros, Yonina C. Eldar

We employ the Cram\'er-Rao bound (CRB) as a performance metric of target estimation, under both point and extended target scenarios.

Joint Radar-Communication

On Provable Backdoor Defense in Collaborative Learning

no code implementations19 Jan 2021 Ximing Qiao, Yuhua Bai, Siping Hu, Ang Li, Yiran Chen, Hai Li

The framework shows that the subset selection process, a deciding factor for subset aggregation methods, can be viewed as a code design problem.

backdoor defense

GenQu: A Hybrid Framework for Learning Classical Data in Quantum States

no code implementations1 Jan 2021 Samuel A. Stein, Ray Marie Tischio, Betis Baheri, YiWen Chen, Ying Mao, Qiang Guan, Ang Li, Bo Fang

In this paper, we propose GenQu, a hybrid and general-purpose quantum framework for learning classical data through quantum states.

GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs

no code implementations8 Dec 2020 Binghui Wang, Ang Li, Hai Li, Yiran Chen

However, existing FL methods 1) perform poorly when data across clients are non-IID, 2) cannot handle data with new label domains, and 3) cannot leverage unlabeled data, while all these issues naturally happen in real-world graph-based problems.

Federated Learning General Classification +2

Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective

4 code implementations8 Dec 2020 Jingwei Sun, Ang Li, Binghui Wang, Huanrui Yang, Hai Li, Yiran Chen

In this work, we show our key observation that the data representation leakage from gradients is the essential cause of privacy leakage in FL.

Federated Learning

Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function

1 code implementation1 Sep 2020 Binghui Wang, Tianxiang Zhou, Minhua Lin, Pan Zhou, Ang Li, Meng Pang, Hai Li, Yiran Chen

Specifically, we first introduce two influence functions, i. e., feature-label influence and label influence, that are defined on GNNs and label propagation (LP), respectively.

Node Classification

Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs

no code implementations1 Sep 2020 Houxiang Fan, Binghui Wang, Pan Zhou, Ang Li, Meng Pang, Zichuan Xu, Cai Fu, Hai Li, Yiran Chen

Link prediction in dynamic graphs (LPDG) is an important research problem that has diverse applications such as online recommendations, studies on disease contagion, organizational studies, etc.

Graph Embedding Link Prediction +2

LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets

1 code implementation7 Aug 2020 Ang Li, Jingwei Sun, Binghui Wang, Lin Duan, Sicheng Li, Yiran Chen, Hai Li

Rather than learning a shared global model in classic federated learning, each client learns a personalized model via LotteryFL; the communication cost can be significantly reduced due to the compact size of lottery networks.

Federated Learning

Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUs

1 code implementation30 Jun 2020 Ang Li, Simon Su

Despite foreseeing tremendous speedups over conventional deep neural networks, the performance advantage of binarized neural networks (BNNs) has merely been showcased on general-purpose processors such as CPUs and GPUs.

Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint

no code implementations19 Jun 2020 Dong Yin, Mehrdad Farajtabar, Ang Li, Nir Levine, Alex Mott

This problem is often referred to as catastrophic forgetting, a key challenge in continual learning of neural networks.

Continual Learning

Learning to Incentivize Other Learning Agents

2 code implementations NeurIPS 2020 Jiachen Yang, Ang Li, Mehrdad Farajtabar, Peter Sunehag, Edward Hughes, Hongyuan Zha

The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years.

General Reinforcement Learning Reinforcement Learning (RL)

QASMBench: A Low-level QASM Benchmark Suite for NISQ Evaluation and Simulation

4 code implementations26 May 2020 Ang Li, Sriram Krishnamoorthy

For evaluation, we measure the execution fidelity of a subset of QASMBench applications on 12 IBM-Q machines through density matrix state tomography, which comprises 25K circuit evaluations.

Quantum Physics

PoliteCamera: Respecting Strangers' Privacy in Mobile Photographing

no code implementations24 May 2020 Ang Li, Wei Du, Qinghua Li

Through the cooperation between a photographer and a stranger, the stranger's face in a photo can be automatically blurred upon his request when the photo is taken.

MVStylizer: An Efficient Edge-Assisted Video Photorealistic Style Transfer System for Mobile Phones

no code implementations24 May 2020 Ang Li, Chunpeng Wu, Yiran Chen, Bin Ni

Instead of performing stylization frame by frame, only key frames in the original video are processed by a pre-trained deep neural network (DNN) on edge servers, while the rest of stylized intermediate frames are generated by our designed optical-flow-based frame interpolation algorithm on mobile phones.

Federated Learning Optical Flow Estimation +2

TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations

no code implementations23 May 2020 Ang Li, Yixiao Duan, Huanrui Yang, Yiran Chen, Jianlei Yang

The goal of this framework is to learn a feature extractor that can hide the privacy information from the intermediate representations; while maximally retaining the original information embedded in the raw data for the data collector to accomplish unknown learning tasks.

Tidal deformability and gravitational-wave phase evolution of magnetised compact-star binaries

no code implementations6 May 2020 Zhenyu Zhu, Ang Li, Luciano Rezzolla

Hence, the measurement of these corrections has the potential of providing important information on the equation of state of nuclear matter.

High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology

Reconfigurable Intelligent Surface (RIS)-Enhanced Two-Way OFDM Communications

no code implementations5 May 2020 Chandan Pradhan, Ang Li, Lingyang Song, Jun Li, Branka Vucetic, Yonghui Li

In this paper, we focus on the reconfigurable intelligent surface (RIS)-enhanced two-way device-to-device (D2D) multi-pair orthogonal-frequency-division-multiplexing (OFDM) communication systems.

Vocal Bursts Valence Prediction

The AVA-Kinetics Localized Human Actions Video Dataset

no code implementations1 May 2020 Ang Li, Meghana Thotakuri, David A. Ross, João Carreira, Alexander Vostrikov, Andrew Zisserman

The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these new AVA annotated Kinetics clips.

Action Classification

Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification

1 code implementation20 Apr 2020 Huanrui Yang, Minxue Tang, Wei Wen, Feng Yan, Daniel Hu, Ang Li, Hai Li, Yiran Chen

In this work, we propose SVD training, the first method to explicitly achieve low-rank DNNs during training without applying SVD on every step.

Hybrid Models for Open Set Recognition

no code implementations ECCV 2020 Hongjie Zhang, Ang Li, Jie Guo, Yanwen Guo

We propose the OpenHybrid framework, which is composed of an encoder to encode the input data into a joint embedding space, a classifier to classify samples to inlier classes, and a flow-based density estimator to detect whether a sample belongs to the unknown category.

Open Set Learning Out-of-Distribution Detection

Orthogonal Gradient Descent for Continual Learning

no code implementations15 Oct 2019 Mehrdad Farajtabar, Navid Azizan, Alex Mott, Ang Li

In this paper, we propose to address this issue from a parameter space perspective and study an approach to restrict the direction of the gradient updates to avoid forgetting previously-learned data.

Continual Learning

DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones

no code implementations9 Sep 2019 Ang Li, Jiayi Guo, Huanrui Yang, Flora D. Salim, Yiran Chen

Our experiments on CelebA and LFW datasets show that the quality of the reconstructed images from the obfuscated features of the raw image is dramatically decreased from 0. 9458 to 0. 3175 in terms of multi-scale structural similarity.

General Classification Image Classification +3

Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control

1 code implementation ICLR 2020 Nir Levine, Yin-Lam Chow, Rui Shu, Ang Li, Mohammad Ghavamzadeh, Hung Bui

A promising approach is to embed the high-dimensional observations into a lower-dimensional latent representation space, estimate the latent dynamics model, then utilize this model for control in the latent space.

Decision Making Open-Ended Question Answering +1

Boosted GAN with Semantically Interpretable Information for Image Inpainting

no code implementations13 Aug 2019 Ang Li, Jianzhong Qi, Rui Zhang, Ramamohanarao Kotagiri

Forexample, given a male image with image region of one eye missing, current models may restore it with a female eye.

Attribute Image Inpainting +2

Generative Image Inpainting with Submanifold Alignment

no code implementations1 Aug 2019 Ang Li, Jianzhong Qi, Rui Zhang, Xingjun Ma, Kotagiri Ramamohanarao

Image inpainting aims at restoring missing regions of corrupted images, which has many applications such as image restoration and object removal.

Image Inpainting Image Restoration

PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving

no code implementations CVPR 2020 Zelun Kong, Junfeng Guo, Ang Li, Cong Liu

We compare PhysGAN with a set of state-of-the-art baseline methods including several of our self-designed ones, which further demonstrate the robustness and efficacy of our approach.

Autonomous Driving Image Classification

Cross-View Policy Learning for Street Navigation

1 code implementation ICCV 2019 Ang Li, Huiyi Hu, Piotr Mirowski, Mehrdad Farajtabar

The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL).

Navigate Reinforcement Learning (RL) +1

Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect

1 code implementation11 Mar 2019 Ang Li, Shuaiwen Leon Song, Jieyang Chen, Jiajia Li, Xu Liu, Nathan Tallent, Kevin Barker

High performance multi-GPU computing becomes an inevitable trend due to the ever-increasing demand on computation capability in emerging domains such as deep learning, big data and planet-scale simulations.

Hardware Architecture Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Performance

Improved Knowledge Distillation via Teacher Assistant

3 code implementations9 Feb 2019 Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Ang Li, Nir Levine, Akihiro Matsukawa, Hassan Ghasemzadeh

To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher.

Knowledge Distillation

A Generalized Framework for Population Based Training

no code implementations5 Feb 2019 Ang Li, Ola Spyra, Sagi Perel, Valentin Dalibard, Max Jaderberg, Chenjie Gu, David Budden, Tim Harley, Pramod Gupta

Population Based Training (PBT) is a recent approach that jointly optimizes neural network weights and hyperparameters which periodically copies weights of the best performers and mutates hyperparameters during training.

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters

no code implementations4 Jan 2019 Tong Geng, Tianqi Wang, Ang Li, Xi Jin, Martin Herbordt

Among the issues with this approach is that to make the distributed cluster work with high utilization, the workload distributed to each node must be large, which implies nontrivial growth in the SGD mini-batch size.

Consistency-aware Shading Orders Selective Fusion for Intrinsic Image Decomposition

no code implementations23 Oct 2018 Yuanliu Liu, Ang Li, Zejian yuan, Badong Chen, Nanning Zheng

We propose a Consistency-aware Selective Fusion (CSF) to integrate the pairwise orders into a globally consistent order.

Intrinsic Image Decomposition

SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection

no code implementations3 Jul 2018 Ang Li, Zejian yuan

Detecting the occlusion from stereo images or video frames is important to many computer vision applications.

Optical Flow Estimation

Layout-induced Video Representation for Recognizing Agent-in-Place Actions

no code implementations ICCV 2019 Ruichi Yu, Hongcheng Wang, Ang Li, Jingxiao Zheng, Vlad I. Morariu, Larry S. Davis

We address the recognition of agent-in-place actions, which are associated with agents who perform them and places where they occur, in the context of outdoor home surveillance.

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

no code implementations13 Jan 2018 Linnan Wang, Jinmian Ye, Yiyang Zhao, Wei Wu, Ang Li, Shuaiwen Leon Song, Zenglin Xu, Tim Kraska

Given the limited GPU DRAM, SuperNeurons not only provisions the necessary memory for the training, but also dynamically allocates the memory for convolution workspaces to achieve the high performance.

Management Scheduling

NISP: Pruning Networks using Neuron Importance Score Propagation

no code implementations CVPR 2018 Ruichi Yu, Ang Li, Chun-Fu Chen, Jui-Hsin Lai, Vlad I. Morariu, Xintong Han, Mingfei Gao, Ching-Yung Lin, Larry S. Davis

In contrast, we argue that it is essential to prune neurons in the entire neuron network jointly based on a unified goal: minimizing the reconstruction error of important responses in the "final response layer" (FRL), which is the second-to-last layer before classification, for a pruned network to retrain its predictive power.

Network Pruning

C-WSL: Count-guided Weakly Supervised Localization

no code implementations ECCV 2018 Mingfei Gao, Ang Li, Ruichi Yu, Vlad I. Morariu, Larry S. Davis

We introduce count-guided weakly supervised localization (C-WSL), an approach that uses per-class object count as a new form of supervision to improve weakly supervised localization (WSL).

Object

Dynamic Zoom-in Network for Fast Object Detection in Large Images

no code implementations CVPR 2018 Mingfei Gao, Ruichi Yu, Ang Li, Vlad I. Morariu, Larry S. Davis

We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images.

object-detection Real-Time Object Detection

Generating Holistic 3D Scene Abstractions for Text-based Image Retrieval

no code implementations CVPR 2017 Ang Li, Jin Sun, Joe Yue-Hei Ng, Ruichi Yu, Vlad I. Morariu, Larry S. Davis

Since interactions between objects can be reduced to a limited set of atomic spatial relations in 3D, we study the possibility of inferring 3D structure from a text description rather than an image, applying physical relation models to synthesize holistic 3D abstract object layouts satisfying the spatial constraints present in a textual description.

Image Retrieval Object +3

ModelHub: Towards Unified Data and Lifecycle Management for Deep Learning

no code implementations18 Nov 2016 Hui Miao, Ang Li, Larry S. Davis, Amol Deshpande

Deep learning modeling lifecycle generates a rich set of data artifacts, such as learned parameters and training logs, and comprises of several frequently conducted tasks, e. g., to understand the model behaviors and to try out new models.

Management

Coordinating Multiple Disparity Proposals for Stereo Computation

no code implementations CVPR 2016 Ang Li, Dapeng Chen, Yuanliu liu, Zejian yuan

While great progress has been made in stereo computation over the last decades, large textureless regions remain challenging.

Sensing Subjective Well-being from Social Media

no code implementations15 Mar 2014 Bibo Hao, Lin Li, Rui Gao, Ang Li, Tingshao Zhu

Nowadays, people are motivated to share their experiences and feelings on social media, so we propose to sense SWB from the vast user generated data on social media.

Cannot find the paper you are looking for? You can Submit a new open access paper.