Search Results for author: Xiang Chen

Found 139 papers, 56 papers with code

Collaborative Feedback Discriminative Propagation for Video Super-Resolution

1 code implementation6 Apr 2024 Hao Li, Xiang Chen, Jiangxin Dong, Jinhui Tang, Jinshan Pan

However, inaccurate alignment usually leads to aligned features with significant artifacts, which will be accumulated during propagation and thus affect video restoration.

Video Reconstruction Video Restoration +1

Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining

1 code implementation2 Apr 2024 Xiang Chen, Jinshan Pan, Jiangxin Dong

To better explore the common degradation representations from spatially-varying rain streaks, we incorporate intra-scale implicit neural representations based on pixel coordinates with the degraded inputs in a closed-loop design, enabling the learned features to facilitate rain removal and improve the robustness of the model in complex scenarios.

Image Reconstruction Rain Removal

Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble

no code implementations24 Mar 2024 Chenhui Xu, Fuxun Yu, Zirui Xu, Nathan Inkawhich, Xiang Chen

Our experimental results demonstrate the superior performance of the MC Ensemble strategy in OOD detection compared to both the naive Deep Ensemble method and a standalone model of comparable size.

Out-of-Distribution Detection

WikiTableEdit: A Benchmark for Table Editing by Natural Language Instruction

no code implementations5 Mar 2024 Zheng Li, Xiang Chen, Xiaojun Wan

Subsequently, we evaluate several representative large language models on the WikiTableEdit dataset to demonstrate the challenge of this task.

HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances

no code implementations4 Mar 2024 Supreeth Narasimhaswamy, Uttaran Bhattacharya, Xiang Chen, Ishita Dasgupta, Saayan Mitra, Minh Hoai

To generate images with realistic hands, we propose a novel diffusion-based architecture called HanDiffuser that achieves realism by injecting hand embeddings in the generative process.

Text-to-Image Generation

An inexact Bregman proximal point method and its acceleration version for unbalanced optimal transport

no code implementations26 Feb 2024 Xiang Chen, Faqiang Wang, Jun Liu, Li Cui

The algorithm (1) converges to the true solution of UOT, (2) has theoretical guarantees and robust regularization parameter selection, (3) mitigates numerical stability issues, and (4) can achieve comparable computational complexity to the Scaling algorithm in specific practice.

Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models

no code implementations22 Feb 2024 Younghun Lee, Sungchul Kim, Tong Yu, Ryan A. Rossi, Xiang Chen

The model learns to reduce the input context using On-Policy Reinforcement Learning and aims to improve the reasoning performance of a fixed LLM.

Language Modelling

UAV-Rain1k: A Benchmark for Raindrop Removal from UAV Aerial Imagery

1 code implementation8 Feb 2024 Wenhui Chang, Hongming Chen, Xin He, Xiang Chen, Liangduo Shen

Raindrops adhering to the lens of UAVs can obstruct visibility of the background scene and degrade image quality.

Rain Removal

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

2 code implementations8 Feb 2024 Zhuo Chen, Yichi Zhang, Yin Fang, Yuxia Geng, Lingbing Guo, Xiang Chen, Qian Li, Wen Zhang, Jiaoyan Chen, Yushan Zhu, Jiaqi Li, Xiaoze Liu, Jeff Z. Pan, Ningyu Zhang, Huajun Chen

In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm.

Entity Alignment Image Classification +4

Unified Hallucination Detection for Multimodal Large Language Models

1 code implementation5 Feb 2024 Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Despite significant strides in multimodal tasks, Multimodal Large Language Models (MLLMs) are plagued by the critical issue of hallucination.


Slicer Networks

no code implementations18 Jan 2024 Hang Zhang, Xiang Chen, Rongguang Wang, Renjiu Hu, Dongdong Liu, Gaolei Li

In medical imaging, scans often reveal objects with varied contrasts but consistent internal intensities or textures.

Image Registration Lesion Segmentation +1

RJUA-QA: A Comprehensive QA Dataset for Urology

1 code implementation15 Dec 2023 Shiwei Lyu, Chenfei Chi, Hongbo Cai, Lei Shi, Xiaoyan Yang, Lei Liu, Xiang Chen, Deng Zhao, Zhiqiang Zhang, Xianguo Lyu, Ming Zhang, Fangzhou Li, Xiaowei Ma, Yue Shen, Jinjie Gu, Wei Xue, Yiran Huang

We introduce RJUA-QA, a novel medical dataset for question answering (QA) and reasoning with clinical evidence, contributing to bridge the gap between general large language models (LLMs) and medical-specific LLM applications.

Question Answering

Multi-Objective Complementary Control

no code implementations15 Dec 2023 Jiapeng Xu, Xiang Chen, Ying Tan, Kemin Zhou

This paper proposes a novel multi-objective control framework for linear time-invariant systems in which performance and robustness can be achieved in a complementary way instead of trade-off.

Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?

1 code implementation1 Dec 2023 Weisong Sun, Chunrong Fang, Yun Miao, Yudu You, Mengzhe Yuan, Yuchen Chen, Quanjun Zhang, An Guo, Xiang Chen, Yang Liu, Zhenyu Chen

To do so, we compare the performance of models trained with code token sequence (Token for short) based code representation and AST-based code representation on three popular types of code-related tasks.

Representation Learning

QuadraNet: Improving High-Order Neural Interaction Efficiency with Hardware-Aware Quadratic Neural Networks

no code implementations29 Nov 2023 Chenhui Xu, Fuxun Yu, Zirui Xu, ChenChen Liu, JinJun Xiong, Xiang Chen

Recent progress in computer vision-oriented neural network designs is mostly driven by capturing high-order neural interactions among inputs and features.

Hardware Aware Neural Architecture Search Neural Architecture Search

Spatially Covariant Image Registration with Text Prompts

1 code implementation27 Nov 2023 Xiang Chen, Min Liu, Rongguang Wang, Renjiu Hu, Dongdong Liu, Gaolei Li, Hang Zhang

Medical images are often characterized by their structured anatomical representations and spatially inhomogeneous contrasts.

Ranked #2 on Image Registration on Unpaired-abdomen-CT (using extra training data)

Computational Efficiency Image Registration +2

HiFi-Syn: Hierarchical Granularity Discrimination for High-Fidelity Synthesis of MR Images with Structure Preservation

no code implementations21 Nov 2023 Ziqi Yu, Botao Zhao, Shengjie Zhang, Xiang Chen, Jianfeng Feng, Tingying Peng, Xiao-Yong Zhang

To address these issues, we introduce hierarchical granularity discrimination, which exploits various levels of semantic information present in medical images.


Decentralized Personalized Online Federated Learning

no code implementations8 Nov 2023 Renzhi Wu, Saayan Mitra, Xiang Chen, Anup Rao

Therefore, we propose a new learning setting \textit{Decentralized Personalized Online Federated Learning} that considers all the three aspects at the same time.

Federated Learning

Foundation Model Based Native AI Framework in 6G with Cloud-Edge-End Collaboration

no code implementations26 Oct 2023 Xiang Chen, Zhiheng Guo, Xijun Wang, Howard H. Yang, Chenyuan Feng, Junshen Su, Sihui Zheng, Tony Q. S. Quek

Future wireless communication networks are in a position to move beyond data-centric, device-oriented connectivity and offer intelligent, immersive experiences based on task-oriented connections, especially in the context of the thriving development of pre-trained foundation models (PFM) and the evolving vision of 6G native artificial intelligence (AI).

Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models

no code implementations25 Oct 2023 Xiang Chen, Xiaojun Wan

Advancements in natural language generation (NLG) and large language models (LLMs) have led to proficient text generation in various tasks.

Text Generation

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search

no code implementations20 Oct 2023 Yuchen Zhuang, Xiang Chen, Tong Yu, Saayan Mitra, Victor Bursztyn, Ryan A. Rossi, Somdeb Sarkhel, Chao Zhang

It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan.

Decision Making valid

FactCHD: Benchmarking Fact-Conflicting Hallucination Detection

1 code implementation18 Oct 2023 Xiang Chen, Duanzheng Song, Honghao Gui, Chenxi Wang, Ningyu Zhang, Jiang Yong, Fei Huang, Chengfei Lv, Dan Zhang, Huajun Chen

Despite their impressive generative capabilities, LLMs are hindered by fact-conflicting hallucinations in real-world applications.

Benchmarking Hallucination

WikiIns: A High-Quality Dataset for Controlled Text Editing by Natural Language Instruction

1 code implementation8 Oct 2023 Xiang Chen, Zheng Li, Xiaojun Wan

In this paper, we study the problem of controlled text editing by natural language instruction.


Towards Unified Deep Image Deraining: A Survey and A New Benchmark

no code implementations5 Oct 2023 Xiang Chen, Jinshan Pan, Jiangxin Dong, Jinhui Tang

In this paper, we provide a comprehensive review of existing image deraining method and provide a unify evaluation setting to evaluate the performance of image deraining methods.

Rain Removal

CPPF: A contextual and post-processing-free model for automatic speech recognition

no code implementations14 Sep 2023 Lei Zhang, Zhengkun Tian, Xiang Chen, Jiaming Sun, Hongyu Xiang, Ke Ding, Guanglu Wan

To address this issue, we draw inspiration from the multifaceted capabilities of LLMs and Whisper, and focus on integrating multiple ASR text processing tasks related to speech recognition into the ASR model.

Automatic Speech Recognition speech-recognition +1

DAGrid: Directed Accumulator Grid

1 code implementation5 Jun 2023 Hang Zhang, Renjiu Hu, Xiang Chen, Rongguang Wang, Jinwei Zhang, Jiahao Li

Specifically, the network incorporating DAGrid has realized a 70. 8% reduction in network parameter size and a 96. 8% decrease in FLOPs, while concurrently improving the Dice score for skin lesion segmentation by 1. 0% compared to state-of-the-art transformers.

Image Registration Lesion Segmentation +1

Unsupervised Massive MIMO Channel Estimation with Dual-Path Knowledge-Aware Auto-Encoders

no code implementations30 May 2023 Zhiheng Guo, Yuanzhang Xiao, Xiang Chen

In this paper, an unsupervised deep learning framework based on dual-path model-driven variational auto-encoders (VAE) is proposed for angle-of-arrivals (AoAs) and channel estimation in massive MIMO systems.

DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling

1 code implementation30 May 2023 Yuchen Zhuang, Yue Yu, Lingkai Kong, Xiang Chen, Chao Zhang

Most existing methods for learning from noisy labels use static input features for denoising, but these methods are limited by the information they can provide on true label distributions and can result in biased or incorrect predictions.


Continual Multimodal Knowledge Graph Construction

1 code implementation15 May 2023 Xiang Chen, Ningyu Zhang, Jintian Zhang, Xiaohan Wang, Tongtong Wu, Xi Chen, Yongheng Wang, Huajun Chen

Multimodal Knowledge Graph Construction (MKGC) involves creating structured representations of entities and relations using multiple modalities, such as text and images.

Continual Learning graph construction +1

Loop Closure Detection Based on Object-level Spatial Layout and Semantic Consistency

1 code implementation11 Apr 2023 Xingwu Ji, Peilin Liu, Haochen Niu, Xiang Chen, Rendong Ying, Fei Wen

Then, we propose a graph matching approach to select correspondence objects based on the structure layout and semantic property similarity of vertices' neighbors.

Graph Matching Loop Closure Detection +2

Robust Tracking Control for Nonlinear Systems: Performance optimization via extremum seeking

no code implementations31 Mar 2023 Jiapeng Xu, Ying Tan, Xiang Chen

This paper presents a controller design and optimization framework for nonlinear dynamic systems to track a given reference signal in the presence of disturbances when the task is repeated over a finite-time interval.

Learning A Sparse Transformer Network for Effective Image Deraining

1 code implementation CVPR 2023 Xiang Chen, Hao Li, Mingqiang Li, Jinshan Pan

To overcome this problem, we propose an effective DeRaining network, Sparse Transformer (DRSformer) that can adaptively keep the most useful self-attention values for feature aggregation so that the aggregated features better facilitate high-quality image reconstruction.

Image Reconstruction Image Restoration +1

Self-Supervised Interest Transfer Network via Prototypical Contrastive Learning for Recommendation

no code implementations28 Feb 2023 Guoqiang Sun, Yibin Shen, Sijin Zhou, Xiang Chen, Hongyan Liu, Chunming Wu, Chenyi Lei, Xianhui Wei, Fei Fang

In this paper, we propose a cross-domain recommendation method: Self-supervised Interest Transfer Network (SITN), which can effectively transfer invariant knowledge between domains via prototypical contrastive learning.

Contrastive Learning

Binary Embedding-based Retrieval at Tencent

1 code implementation17 Feb 2023 Yukang Gan, Yixiao Ge, Chang Zhou, Shupeng Su, Zhouchuan Xu, Xuyuan Xu, Quanchao Hui, Xiang Chen, Yexin Wang, Ying Shan

To tackle the challenge, we propose a binary embedding-based retrieval (BEBR) engine equipped with a recurrent binarization algorithm that enables customized bits per dimension.

Binarization Retrieval

One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NER

2 code implementations25 Jan 2023 Xiang Chen, Lei LI, Shuofei Qiao, Ningyu Zhang, Chuanqi Tan, Yong Jiang, Fei Huang, Huajun Chen

Previous typical solutions mainly obtain a NER model by pre-trained language models (PLMs) with data from a rich-resource domain and adapt it to the target domain.

NER Text Generation

Reasoning with Language Model Prompting: A Survey

2 code implementations19 Dec 2022 Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Huajun Chen

Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc.

Arithmetic Reasoning Common Sense Reasoning +4

On Robust Observer Design for System Motion on SE(3) Using Onboard Visual Sensors

no code implementations29 Nov 2022 Tong Zhang, Ying Tan, Xiang Chen, Zike Lei

The key design idea for this observer is to estimate the visible set and identify the mis-identified features from the measurements.

Robust output regulation of linear system subject to modeled and unmodeled uncertainty

no code implementations27 Oct 2022 Zhicheng Zhang, Zhiqiang Zuo, Xiang Chen, Ying Tan, Yijing Wang

The output regulation scheme is utilized in the framework to track the reference in the presence of modeled disturbance, and the effect of unmodeled disturbance is reduced by an $\mathcal{H}_\infty$ compensator.

Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction

1 code implementation19 Oct 2022 Yunzhi Yao, Shengyu Mao, Ningyu Zhang, Xiang Chen, Shumin Deng, Xi Chen, Huajun Chen

With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance.

Event Extraction graph construction +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

QC-ODKLA: Quantized and Communication-Censored Online Decentralized Kernel Learning via Linearized ADMM

no code implementations4 Aug 2022 Ping Xu, Yue Wang, Xiang Chen, Zhi Tian

We then propose a novel learning framework named Online Decentralized Kernel learning via Linearized ADMM (ODKLA) to efficiently solve the online decentralized kernel learning problem.


Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning

2 code implementations29 May 2022 Xiang Chen, Lei LI, Ningyu Zhang, Xiaozhuan Liang, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

Specifically, vanilla prompt learning may struggle to utilize atypical instances by rote during fully-supervised training or overfit shallow patterns with low-shot data.

Few-Shot Text Classification Memorization +5

Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction

1 code implementation7 May 2022 Xiang Chen, Ningyu Zhang, Lei LI, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

To deal with these issues, we propose a novel Hierarchical Visual Prefix fusion NeTwork (HVPNeT) for visual-enhanced entity and relation extraction, aiming to achieve more effective and robust performance.

named-entity-recognition Named Entity Recognition +3

Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

1 code implementation4 May 2022 Xiang Chen, Ningyu Zhang, Lei LI, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen

Since most MKGs are far from complete, extensive knowledge graph completion studies have been proposed focusing on the multimodal entity, relation extraction and link prediction.

Information Retrieval Link Prediction +4

Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning

1 code implementation4 May 2022 Xiang Chen, Lei LI, Ningyu Zhang, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

Note that the previous parametric learning paradigm can be viewed as memorization regarding training data as a book and inference as the close-book test.

Few-Shot Learning Memorization +3

BI-GreenNet: Learning Green's functions by boundary integral network

no code implementations28 Apr 2022 Guochang Lin, Fukai Chen, Pipi Hu, Xiang Chen, Junqing Chen, Jun Wang, Zuoqiang Shi

In addition, we also use the Green's function calculated by our method to solve a class of PDE, and also obtain high-precision solutions, which shows the good generalization ability of our method on solving PDEs.

M2N: Mesh Movement Networks for PDE Solvers

1 code implementation24 Apr 2022 Wenbin Song, Mingrui Zhang, Joseph G. Wallwork, Junpeng Gao, Zheng Tian, Fanglei Sun, Matthew D. Piggott, Junqing Chen, Zuoqiang Shi, Xiang Chen, Jun Wang

However, mesh movement methods, such as the Monge-Ampere method, require the solution of auxiliary equations, which can be extremely expensive especially when the mesh is adapted frequently.

Graph Attention

Dense Learning based Semi-Supervised Object Detection

1 code implementation CVPR 2022 Binghui Chen, Pengyu Li, Xiang Chen, Biao Wang, Lei Zhang, Xian-Sheng Hua

Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data.

Object object-detection +2

QuadraLib: A Performant Quadratic Neural Network Library for Architecture Optimization and Design Exploration

no code implementations1 Apr 2022 Zirui Xu, Fuxun Yu, JinJun Xiong, Xiang Chen

The significant success of Deep Neural Networks (DNNs) is highly promoted by the multiple sophisticated DNN libraries.

Optimization of Directional Landmark Deployment for Visual Observer on SE(3)

no code implementations28 Mar 2022 Zike Lei, Xi Chen, Ying Tan, Xiang Chen, Li Chai

An optimization method is proposed in this paper for novel deployment of given number of directional landmarks (location and pose) within a given region in the 3-D task space.


NeuralReshaper: Single-image Human-body Retouching with Deep Neural Networks

no code implementations20 Mar 2022 Beijia Chen, Yuefan Shen, Hongbo Fu, Xiang Chen, Kun Zhou, Youyi Zheng

In this paper, we present NeuralReshaper, a novel method for semantic reshaping of human bodies in single images using deep generative networks.

Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning

no code implementations15 Mar 2022 Xiang Chen, Zhentao Fan, Pengpeng Li, Longgang Dai, Caihua Kong, Zhuoran Zheng, Yufeng Huang, Yufeng Li

Then these negative adversaries are trained end-to-end together with the backbone representation network to enhance the discriminative information and promote factor disentanglement performance by maximizing the adversarial contrastive loss.

Contrastive Learning Disentanglement +3

Single UHD Image Dehazing via Interpretable Pyramid Network

1 code implementation17 Feb 2022 Boxue Xiao, Zhuoran Zheng, Xiang Chen, Chen Lv, Yunliang Zhuang, Tao Wang

Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time.

Image Dehazing Single Image Dehazing

AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems

no code implementations10 Feb 2022 Yingzhanghao Zhou, Xiang Chen, Peng Zhang, Jun Wang, Lei Wang, Hong Guo

Since proposed in the 70s, the Non-Equilibrium Green Function (NEGF) method has been recognized as a standard approach to quantum transport simulations.

A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis

1 code implementation29 Jan 2022 Xiang Chen, Xiaojun Wan

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task which aims to extract the aspects from sentences and identify their corresponding sentiments.

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

Ontology-enhanced Prompt-tuning for Few-shot Learning

no code implementations27 Jan 2022 Hongbin Ye, Ningyu Zhang, Shumin Deng, Xiang Chen, Hui Chen, Feiyu Xiong, Xi Chen, Huajun Chen

Specifically, we develop the ontology transformation based on the external knowledge graph to address the knowledge missing issue, which fulfills and converts structure knowledge to text.

Event Extraction Few-Shot Learning +1

TPAD: Identifying Effective Trajectory Predictions Under the Guidance of Trajectory Anomaly Detection Model

no code implementations9 Jan 2022 Chunnan Wang, Chen Liang, Xiang Chen, Hongzhi Wang

They are lack of self-evaluation ability, that is, to examine the rationality of their prediction results, thus failing to guide users to identify high-quality ones from their candidate results.

Anomaly Detection AutoML +1

ATPFL: Automatic Trajectory Prediction Model Design Under Federated Learning Framework

no code implementations CVPR 2022 Chunnan Wang, Xiang Chen, Junzhe Wang, Hongzhi Wang

Although the Trajectory Prediction (TP) model has achieved great success in computer vision and robotics fields, its architecture and training scheme design rely on heavy manual work and domain knowledge, which is not friendly to common users.

Federated Learning Trajectory Prediction

Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art

1 code implementation23 Dec 2021 Xiang Ling, Lingfei Wu, Jiangyu Zhang, Zhenqing Qu, Wei Deng, Xiang Chen, Yaguan Qian, Chunming Wu, Shouling Ji, Tianyue Luo, Jingzheng Wu, Yanjun Wu

Then, we conduct a comprehensive and systematic review to categorize the state-of-the-art adversarial attacks against PE malware detection, as well as corresponding defenses to increase the robustness of Windows PE malware detection.

Adversarial Attack Malware Detection +2

Fed2: Feature-Aligned Federated Learning

no code implementations28 Nov 2021 Fuxun Yu, Weishan Zhang, Zhuwei Qin, Zirui Xu, Di Wang, ChenChen Liu, Zhi Tian, Xiang Chen

Federated learning learns from scattered data by fusing collaborative models from local nodes.

Federated Learning

A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities

no code implementations28 Nov 2021 Fuxun Yu, Di Wang, Longfei Shangguan, Minjia Zhang, Xulong Tang, ChenChen Liu, Xiang Chen

With both scaling trends, new problems and challenges emerge in DL inference serving systems, which gradually trends towards Large-scale Deep learning Serving systems (LDS).

A neural network framework for learning Green's function

no code implementations29 Sep 2021 Guochang Lin, Fukai Chen, Pipi Hu, Xiang Chen, Junqing Chen, Jun Wang, Zuoqiang Shi

Green's function plays a significant role in both theoretical analysis and numerical computing of partial differential equations (PDEs).

Performance-Guaranteed ODE Solvers with Complexity-Informed Neural Networks

no code implementations NeurIPS Workshop DLDE 2021 Feng Zhao, Xiang Chen, Jun Wang, Zuoqiang Shi, Shao-Lun Huang

Traditionally, we provide technical parameters for ODE solvers, such as the order, the stepsize and the local error threshold.

SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis

no code implementations17 Sep 2021 Chengxi Li, Feiyu Gao, Jiajun Bu, Lu Xu, Xiang Chen, Yu Gu, Zirui Shao, Qi Zheng, Ningyu Zhang, Yongpan Wang, Zhi Yu

We inject sentiment knowledge regarding aspects, opinions, and polarities into prompt and explicitly model term relations via constructing consistency and polarity judgment templates from the ground truth triplets.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3

Unpaired Deep Image Deraining Using Dual Contrastive Learning

no code implementations CVPR 2022 Xiang Chen, Jinshan Pan, Kui Jiang, Yufeng Li, Yufeng Huang, Caihua Kong, Longgang Dai, Zhentao Fan

Learning single image deraining (SID) networks from an unpaired set of clean and rainy images is practical and valuable as acquiring paired real-world data is almost infeasible.

Contrastive Learning Image Restoration +1

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

4 code implementations ICLR 2022 Ningyu Zhang, Luoqiu Li, Xiang Chen, Shumin Deng, Zhen Bi, Chuanqi Tan, Fei Huang, Huajun Chen

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners.

Language Modelling Prompt Engineering

A Deep Discontinuity-Preserving Image Registration Network

1 code implementation9 Jul 2021 Xiang Chen, Nishant Ravikumar, Yan Xia, Alejandro F Frangi

Image registration aims to establish spatial correspondence across pairs, or groups of images, and is a cornerstone of medical image computing and computer-assisted-interventions.

Image Registration Medical Image Registration +1

Document-level Relation Extraction as Semantic Segmentation

2 code implementations7 Jun 2021 Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng, Chuanqi Tan, Mosha Chen, Fei Huang, Luo Si, Huajun Chen

Specifically, we leverage an encoder module to capture the context information of entities and a U-shaped segmentation module over the image-style feature map to capture global interdependency among triples.

Document-level Relation Extraction Relation +2

Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining

no code implementations25 Apr 2021 Xiang Chen, Yufeng Huang, Lei Xu

Rain streaks bring serious blurring and visual quality degradation, which often vary in size, direction and density.

Single Image Deraining

KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction

1 code implementation15 Apr 2021 Xiang Chen, Ningyu Zhang, Xin Xie, Shumin Deng, Yunzhi Yao, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

To this end, we focus on incorporating knowledge among relation labels into prompt-tuning for relation extraction and propose a Knowledge-aware Prompt-tuning approach with synergistic optimization (KnowPrompt).

Ranked #5 on Dialog Relation Extraction on DialogRE (F1 (v1) metric)

Dialog Relation Extraction Language Modelling +3

Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challenges

no code implementations14 Apr 2021 Cong Shen, Jie Xu, Sihui Zheng, Xiang Chen

We advocate a new resource allocation framework, which we term resource rationing, for wireless federated learning (FL).

Federated Learning

Disentangled Contrastive Learning for Learning Robust Textual Representations

1 code implementation11 Apr 2021 Xiang Chen, Xin Xie, Zhen Bi, Hongbin Ye, Shumin Deng, Ningyu Zhang, Huajun Chen

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs.

Contrastive Learning

Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction

1 code implementation1 Apr 2021 Luoqiu Li, Xiang Chen, Zhen Bi, Xin Xie, Shumin Deng, Ningyu Zhang, Chuanqi Tan, Mosha Chen, Huajun Chen

Recent neural-based relation extraction approaches, though achieving promising improvement on benchmark datasets, have reported their vulnerability towards adversarial attacks.

Relation Relation Extraction

Proposal for a Bell test in cavity optomagnonics

no code implementations11 Mar 2021 Hong Xie, Zhi-Gao Shi, Le-Wei He, Xiang Chen, Chang-Geng Liao, Xiu-Min Lin

Entanglement between magnon mode and one of the two optical modes will be generated by the first pulse, and the state of magnon mode is subsequently mapped into another optical mode via the second pulse.

Quantum Physics

Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow

1 code implementation1 Feb 2021 Kaibo Cao, Chunyang Chen, Sebastian Baltes, Christoph Treude, Xiang Chen

As query reformulation is tedious for developers, especially for novices, we propose an automated software-specific query reformulation approach based on deep learning.

Towards Robust Textual Representations with Disentangled Contrastive Learning

no code implementations1 Jan 2021 Ningyu Zhang, Xiang Chen, Xin Xie, Shumin Deng, Yantao Jia, Zonggang Yuan, Huajun Chen

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs.

Contrastive Learning

Design and Analysis of Uplink and Downlink Communications for Federated Learning

no code implementations7 Dec 2020 Sihui Zheng, Cong Shen, Xiang Chen

Comprehensive numerical evaluation on various real-world datasets reveals that the benefit of a FL-tailored uplink and downlink communication design is enormous - a carefully designed quantization and transmission achieves more than 98% of the floating-point baseline accuracy with fewer than 10% of the baseline bandwidth, for majority of the experiments on both i. i. d.

Federated Learning Quantization

Directed Graph Attention Neural Network Utilizing 3D Coordinates for Molecular Property Prediction

no code implementations1 Dec 2020 Chen Qian, Yunhai Xiong, Xiang Chen

DGANN distinguishes from previous models with those features: (1) It learns the local chemical environment encoding by graph attention mechanism on chemical bonds.

Graph Attention Molecular Property Prediction +2

Third ArchEdge Workshop: Exploring the Design Space of Efficient Deep Neural Networks

no code implementations22 Nov 2020 Fuxun Yu, Dimitrios Stamoulis, Di Wang, Dimitrios Lymberopoulos, Xiang Chen

This paper gives an overview of our ongoing work on the design space exploration of efficient deep neural networks (DNNs).

Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization

1 code implementation30 Oct 2020 Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer

Due to scarcity of labels on the target domain, we introduce mutual information maximization (MIM) apart from CL to exploit the features that best support the final prediction.

Contrastive Learning General Classification +3

Fourth-Order Nonlocal Tensor Decomposition Model for Spectral Computed Tomography

no code implementations27 Oct 2020 Xiang Chen, Wenjun Xia, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

Spectral computed tomography (CT) can reconstruct spectral images from different energy bins using photon counting detectors (PCDs).

Computed Tomography (CT) Image Reconstruction +1

On Robustness and Bias Analysis of BERT-based Relation Extraction

1 code implementation14 Sep 2020 Luoqiu Li, Xiang Chen, Hongbin Ye, Zhen Bi, Shumin Deng, Ningyu Zhang, Huajun Chen

Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks.

counterfactual Relation +1

MLBF-Net: A Multi-Lead-Branch Fusion Network for Multi-Class Arrhythmia Classification Using 12-Lead ECG

no code implementations17 Aug 2020 Jing Zhang, Deng Liang, Aiping Liu, Min Gao, Xiang Chen, Xu Zhang, Xun Chen

MLBF-Net is composed of three components: 1) multiple lead-specific branches for learning the diversity of multi-lead ECG; 2) cross-lead features fusion by concatenating the output feature maps of all branches for learning the integrity of multi-lead ECG; 3) multi-loss co-optimization for all the individual branches and the concatenated network.

Arrhythmia Detection

Heterogeneous Federated Learning

no code implementations15 Aug 2020 Fuxun Yu, Weishan Zhang, Zhuwei Qin, Zirui Xu, Di Wang, ChenChen Liu, Zhi Tian, Xiang Chen

Specifically, we design a feature-oriented regulation method ({$\Psi$-Net}) to ensure explicit feature information allocation in different neural network structures.

Federated Learning

AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency

no code implementations14 Aug 2020 Fuxun Yu, ChenChen Liu, Di Wang, Yanzhi Wang, Xiang Chen

Based on the neural network attention mechanism, we propose a comprehensive dynamic optimization framework including (1) testing-phase channel and column feature map pruning, as well as (2) training-phase optimization by targeted dropout.

LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery

no code implementations28 May 2020 Wentong Liao, Xiang Chen, Jingfeng Yang, Stefan Roth, Michael Goesele, Michael Ying Yang, Bodo Rosenhahn

This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation.

object-detection Object Detection +1

Generative Feature Replay with Orthogonal Weight Modification for Continual Learning

no code implementations7 May 2020 Gehui Shen, Song Zhang, Xiang Chen, Zhi-Hong Deng

For this scenario, generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting.

Class Incremental Learning Incremental Learning

Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios

no code implementations14 Apr 2020 Baiming Chen, Xiang Chen, Wu Qiong, Liang Li

Results show that the adversarial scenarios generated by our method significantly degrade the performance of the tested vehicles.

Autonomous Driving

Logic-based switching finite-time stabilization with applications in mechanical systems

no code implementations30 Jan 2020 Shiqi Zheng, Shihao Wang, Xiang Chen, Yuanlong Xie

Different from the existing adaptive controllers for structured/parametric uncertainties, a new switching barrier Lyapunov method and supervisory functions are introduced to overcome the obstacles caused by unstructured uncertainties and unknown control directions.

COKE: Communication-Censored Decentralized Kernel Learning

no code implementations28 Jan 2020 Ping Xu, Yue Wang, Xiang Chen, Zhi Tian

This paper studies the decentralized optimization and learning problem where multiple interconnected agents aim to learn an optimal decision function defined over a reproducing kernel Hilbert space by jointly minimizing a global objective function, with access to their own locally observed dataset.

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

no code implementations ECCV 2020 Xiaolong Ma, Wei Niu, Tianyun Zhang, Sijia Liu, Sheng Lin, Hongjia Li, Xiang Chen, Jian Tang, Kaisheng Ma, Bin Ren, Yanzhi Wang

Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms.

Code Generation Compiler Optimization

Helios: Heterogeneity-Aware Federated Learning with Dynamically Balanced Collaboration

no code implementations3 Dec 2019 Zirui Xu, Zhao Yang, JinJun Xiong, Jianlei Yang, Xiang Chen

In this paper, we propose Helios, a heterogeneity-aware FL framework to tackle the straggler issue.

Distributed, Parallel, and Cluster Computing

Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

1 code implementation17 Nov 2019 Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen, Pei Yu, Dimitrios Lymberopoulos, Sidi Lu, Weisong Shi, Xiang Chen

In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors.

Object object-detection +2

LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications

no code implementations17 Oct 2019 Zirui Xu, Fuxun Yu, Xiang Chen

Based on the detection result, we further propose a data recovery methodology to defend the physical adversarial attacks.

Adversarial Attack

Gradient-free Neural Network Training by Multi-convex Alternating Optimization

no code implementations25 Sep 2019 Junxiang Wang, Fuxun Yu, Xiang Chen, Liang Zhao

To overcome these drawbacks, alternating minimization-based methods for deep neural network optimization have attracted fast-increasing attention recently.

Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation

no code implementations27 Aug 2019 Xiaolong Ma, Geng Yuan, Sheng Lin, Caiwen Ding, Fuxun Yu, Tao Liu, Wujie Wen, Xiang Chen, Yanzhi Wang

To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suitable matrix computation and low-power acceleration framework for DNN applications.

Model Compression Quantization

Multi-stage Deep Classifier Cascades for Open World Recognition

1 code implementation26 Aug 2019 Xiaojie Guo, Amir Alipour-Fanid, Lingfei Wu, Hemant Purohit, Xiang Chen, Kai Zeng, Liang Zhao

At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase.

Object Recognition

ADMM for Efficient Deep Learning with Global Convergence

1 code implementation31 May 2019 Junxiang Wang, Fuxun Yu, Xiang Chen, Liang Zhao

However, as an emerging domain, several challenges remain, including 1) The lack of global convergence guarantees, 2) Slow convergence towards solutions, and 3) Cubic time complexity with regard to feature dimensions.

Stochastic Optimization

DoPa: A Comprehensive CNN Detection Methodology against Physical Adversarial Attacks

no code implementations21 May 2019 Zirui Xu, Fuxun Yu, Xiang Chen

To address this issue, we propose DoPa -- a comprehensive CNN detection methodology for various physical adversarial attacks.

Adversarial Attack Detection

Interpreting and Evaluating Neural Network Robustness

no code implementations10 May 2019 Fuxun Yu, Zhuwei Qin, Chenchen Liu, Liang Zhao, Yanzhi Wang, Xiang Chen

Recently, adversarial deception becomes one of the most considerable threats to deep neural networks.

Adversarial Attack


no code implementations ICLR 2019 Zhuwei Qin, Fuxun Yu, ChenChen Liu, Xiang Chen

As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction.

FTGAN: A Fully-trained Generative Adversarial Networks for Text to Face Generation

no code implementations11 Apr 2019 Xiang Chen, Lingbo Qing, Xiaohai He, Xiaodong Luo, Yining Xu

With a novel fully-trained generative network, FTGAN can synthesize higher-quality images and urge the outputs of the FTGAN are more relevant to the input sentences.

Face Generation Generative Adversarial Network +1

DeepCount: Crowd Counting with WiFi via Deep Learning

no code implementations13 Mar 2019 Shangqing Liu, Yanchao Zhao, Fanggang Xue, Bing Chen, Xiang Chen

By massive training samples, our end-to-end learning approach can achieve an average of 86. 4% prediction accuracy in an environment of up to 5 people.

Activity Recognition Crowd Counting

Background Subtraction with Real-time Semantic Segmentation

no code implementations25 Nov 2018 Dongdong Zeng, Xiang Chen, Ming Zhu, Michael Goesele, Arjan Kuijper

Our proposed framework consists of two components, a traditional BGS segmenter $\mathcal{B}$ and a real-time semantic segmenter $\mathcal{S}$.

Foreground Segmentation Object Tracking +1

Demystifying Neural Network Filter Pruning

no code implementations NIPS Workshop CDNNRIA 2018 Zhuwei Qin, Fuxun Yu, ChenChen Liu, Xiang Chen

We find that the filter magnitude based method fails to eliminate the filters with repetitive functionality.

Distilling Critical Paths in Convolutional Neural Networks

no code implementations NIPS Workshop CDNNRIA 2018 Fuxun Yu, Zhuwei Qin, Xiang Chen

Neural network compression and acceleration are widely demanded currently due to the resource constraints on most deployment targets.

Neural Network Compression

Learning color space adaptation from synthetic to real images of cirrus clouds

no code implementations24 Oct 2018 Qing Lyu, Minghao Chen, Xiang Chen

With our adapted synthetic data for training the semantic segmentation, we achieve an improvement of 6:59% when applied to real images, superior to alternative methods.

Segmentation Semantic Segmentation

Functionality-Oriented Convolutional Filter Pruning

no code implementations ICLR 2019 Zhuwei Qin, Fuxun Yu, ChenChen Liu, Xiang Chen

As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction.

Interpreting Adversarial Robustness: A View from Decision Surface in Input Space

no code implementations ICLR 2019 Fuxun Yu, ChenChen Liu, Yanzhi Wang, Liang Zhao, Xiang Chen

One popular hypothesis of neural network generalization is that the flat local minima of loss surface in parameter space leads to good generalization.

Adversarial Robustness

Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients

no code implementations23 May 2018 Fuxun Yu, Zirui Xu, Yanzhi Wang, ChenChen Liu, Xiang Chen

In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications. However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures.

How convolutional neural network see the world - A survey of convolutional neural network visualization methods

1 code implementation30 Apr 2018 Zhuwei Qin, Fuxun Yu, ChenChen Liu, Xiang Chen

Nowadays, the Convolutional Neural Networks (CNNs) have achieved impressive performance on many computer vision related tasks, such as object detection, image recognition, image retrieval, etc.

Image Retrieval object-detection +2

ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction

no code implementations15 Feb 2018 Fuxun Yu, Qide Dong, Xiang Chen

By comparing the analyzed saliency map and the adversarial perturbation distribution, we proposed a new evaluation scheme to comprehensively assess the adversarial attack precision and efficiency.

Adversarial Attack Image Classification +1

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