Search Results for author: Yue Huang

Found 65 papers, 20 papers with code

Optimization-based Prompt Injection Attack to LLM-as-a-Judge

no code implementations26 Mar 2024 Jiawen Shi, Zenghui Yuan, Yinuo Liu, Yue Huang, Pan Zhou, Lichao Sun, Neil Zhenqiang Gong

LLM-as-a-Judge is a novel solution that can assess textual information with large language models (LLMs).

Decision Making

LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?

2 code implementations11 Jan 2024 Qihui Zhang, Chujie Gao, Dongping Chen, Yue Huang, Yixin Huang, Zhenyang Sun, Shilin Zhang, Weiye Li, Zhengyan Fu, Yao Wan, Lichao Sun

With the rapid development and widespread application of Large Language Models (LLMs), the use of Machine-Generated Text (MGT) has become increasingly common, bringing with it potential risks, especially in terms of quality and integrity in fields like news, education, and science.

FakeGPT: Fake News Generation, Explanation and Detection of Large Language Models

no code implementations8 Oct 2023 Yue Huang, Lichao Sun

The rampant spread of fake news has adversely affected society, resulting in extensive research on curbing its spread.

News Generation

Activate and Reject: Towards Safe Domain Generalization under Category Shift

no code implementations ICCV 2023 Chaoqi Chen, Luyao Tang, Leitian Tao, Hong-Yu Zhou, Yue Huang, Xiaoguang Han, Yizhou Yu

Albeit the notable performance on in-domain test points, it is non-trivial for deep neural networks to attain satisfactory accuracy when deploying in the open world, where novel domains and object classes often occur.

Domain Generalization Image Classification +3

MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use

1 code implementation4 Oct 2023 Yue Huang, Jiawen Shi, Yuan Li, Chenrui Fan, Siyuan Wu, Qihui Zhang, Yixin Liu, Pan Zhou, Yao Wan, Neil Zhenqiang Gong, Lichao Sun

However, in scenarios where LLMs serve as intelligent agents, as seen in applications like AutoGPT and MetaGPT, LLMs are expected to engage in intricate decision-making processes that involve deciding whether to employ a tool and selecting the most suitable tool(s) from a collection of available tools to fulfill user requests.

Decision Making

CSPRD: A Financial Policy Retrieval Dataset for Chinese Stock Market

1 code implementation8 Sep 2023 JinYuan Wang, Hai Zhao, Zhong Wang, Zeyang Zhu, Jinhao Xie, Yong Yu, Yongjian Fei, Yue Huang, Dawei Cheng

In recent years, great advances in pre-trained language models (PLMs) have sparked considerable research focus and achieved promising performance on the approach of dense passage retrieval, which aims at retrieving relative passages from massive corpus with given questions.

Passage Retrieval Retrieval

TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models

no code implementations20 Jun 2023 Yue Huang, Qihui Zhang, Philip S. Y, Lichao Sun

Through the implementation of TrustGPT, this research aims to enhance our understanding of the performance of conversation generation models and promote the development of language models that are more ethical and socially responsible.

DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4

1 code implementation20 Mar 2023 Zhengliang Liu, Yue Huang, Xiaowei Yu, Lu Zhang, Zihao Wu, Chao Cao, Haixing Dai, Lin Zhao, Yiwei Li, Peng Shu, Fang Zeng, Lichao Sun, Wei Liu, Dinggang Shen, Quanzheng Li, Tianming Liu, Dajiang Zhu, Xiang Li

The digitization of healthcare has facilitated the sharing and re-using of medical data but has also raised concerns about confidentiality and privacy.

Benchmarking De-identification +4

A Deep Learning Approach for SAR Tomographic Imaging of Forested Areas

no code implementations20 Jan 2023 Zoé Berenger, Loïc Denis, Florence Tupin, Laurent Ferro-Famil, Yue Huang

Synthetic aperture radar tomographic imaging reconstructs the three-dimensional reflectivity of a scene from a set of coherent acquisitions performed in an interferometric configuration.

Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances

1 code implementation CVPR 2023 Zhenqi Fu, Yan Yang, Xiaotong Tu, Yue Huang, Xinghao Ding, Kai-Kuang Ma

Those solutions, however, often fail in revealing image details due to the limited information in a single image and the poor adaptability of handcrafted priors.

Low-Light Image Enhancement

Hint-dynamic Knowledge Distillation

no code implementations30 Nov 2022 Yiyang Liu, Chenxin Li, Xiaotong Tu, Xinghao Ding, Yue Huang

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model.

Knowledge Distillation

Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization

no code implementations14 Oct 2022 Chaoqi Chen, Luyao Tang, Feng Liu, Gangming Zhao, Yue Huang, Yizhou Yu

Domain generalization (DG) enables generalizing a learning machine from multiple seen source domains to an unseen target one.

Domain Generalization Relational Reasoning

Uncertainty Inspired Underwater Image Enhancement

1 code implementation20 Jul 2022 Zhenqi Fu, Wu Wang, Yue Huang, Xinghao Ding, Kai-Kuang Ma

After that, we adopt a consensus process to predict a deterministic result based on a set of samples from the distribution.


Knowledge Condensation Distillation

2 code implementations12 Jul 2022 Chenxin Li, Mingbao Lin, Zhiyuan Ding, Nie Lin, Yihong Zhuang, Yue Huang, Xinghao Ding, Liujuan Cao

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student.

Knowledge Distillation

Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection

no code implementations6 Jun 2022 Chaoqi Chen, Jiongcheng Li, Hong-Yu Zhou, Xiaoguang Han, Yue Huang, Xinghao Ding, Yizhou Yu

However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected.

Domain Adaptation Graph Attention +5

A Closer Look at Personalization in Federated Image Classification

no code implementations22 Apr 2022 Changxing Jing, Yan Huang, Yihong Zhuang, Liyan Sun, Yue Huang, Zhenlong Xiao, Xinghao Ding

This paper shows that it is possible to achieve flexible personalization after the convergence of the global model by introducing representation learning.

Classification Edge-computing +3

AFSC: Adaptive Fourier Space Compression for Anomaly Detection

no code implementations17 Apr 2022 Haote Xu, Yunlong Zhang, Liyan Sun, Chenxin Li, Yue Huang, Xinghao Ding

Data augmentation based methods construct pseudo-healthy images by "pasting" fake lesions on real healthy ones, and a network is trained to predict healthy images in a supervised manner.

Anomaly Detection Data Augmentation

Acoustic-Net: A Novel Neural Network for Sound Localization and Quantification

no code implementations31 Mar 2022 Guanxing Zhou, Hao Liang, Xinghao Ding, Yue Huang, Xiaotong Tu, Saqlain Abbas

Acoustic source localization has been applied in different fields, such as aeronautics and ocean science, generally using multiple microphones array data to reconstruct the source location.

Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis

1 code implementation29 Mar 2022 Yunlong Zhang, Xin Lin, Yihong Zhuang, LiyanSun, Yue Huang, Xinghao Ding, Guisheng Wang, Lin Yang, Yizhou Yu

Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.

Generative Adversarial Network Image Enhancement +4

Self-Verification in Image Denoising

no code implementations1 Nov 2021 Huangxing Lin, Yihong Zhuang, Delu Zeng, Yue Huang, Xinghao Ding, John Paisley

Specifically, we treat the output of the network as a ``prior'' that we denoise again after ``re-noising''.

Image Denoising

GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning

no code implementations11 Jun 2021 Jiajun Fan, Changnan Xiao, Yue Huang

Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process.

Atari Games reinforcement-learning +1

Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation

no code implementations31 May 2021 Chenxin Li, Wenao Ma, Liyan Sun, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu

In this paper, to address the above issues, we propose a hierarchical deep network where an attention mechanism localizes the low-contrast capillary regions guided by the whole vessels, and enhance the spatial activation in those areas for the sub-type vessels.


Self-Regression Learning for Blind Hyperspectral Image Fusion Without Label

no code implementations31 Mar 2021 Wu Wang, Yue Huang, Xinhao Ding

However, in real applications, the observation model involved are often complicated and unknown, which leads to the serious performance drop of many advanced HIF methods.

regression Spectral Reconstruction

I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors

1 code implementation CVPR 2021 Chaoqi Chen, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu

Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers.

Region Proposal

Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation

no code implementations16 Mar 2021 Chenxin Li, Yunlong Zhang, Jiongcheng Li, Yue Huang, Xinghao Ding

In this paper, to alleviate this issue, we introduce the semantic space of healthy anatomy in the process of modeling healthy-data distribution.

Anatomy Anomaly Detection +2

Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification

no code implementations16 Mar 2021 Chenxin Li, Yunlong Zhang, Zhehan Liang, Wenao Ma, Yue Huang, Xinghao Ding

In this paper, we propose a novel vessel-mixing based consistency regularization framework, for cross-domain learning in retinal A/V classification.

Classification General Classification

Urban Surface Reconstruction in SAR Tomography by Graph-Cuts

no code implementations12 Mar 2021 Clément Rambour, Loïc Denis, Florence Tupin, Hélène Oriot, Yue Huang, Laurent Ferro-Famil

This segmentation process can be included within the 3-D reconstruction framework in order to improve the recovery of urban surfaces.

Segmentation Surface Reconstruction

Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement

1 code implementation1 Feb 2021 Zhenqi Fu, Xueyang Fu, Yue Huang, Xinghao Ding

Our approach, termed Twice Mixing, is motivated by the observation that a mid-quality image can be generated by mixing a high-quality image with its low-quality version.


Underwater Image Enhancement via Learning Water Type Desensitized Representations

1 code implementation1 Feb 2021 Zhenqi Fu, Xiaopeng Lin, Wu Wang, Yue Huang, Xinghao Ding

Specifically, we apply whitening to de-correlate activations across spatial dimensions for each instance in a mini-batch.

Image Enhancement Vocal Bursts Type Prediction

Hierarchical Meta Reinforcement Learning for Multi-Task Environments

1 code implementation1 Jan 2021 Dongyang Zhao, Yue Huang, Changnan Xiao, Yue Li, Shihong Deng

To address the problem brought by the environment, we propose a Meta Soft Hierarchical reinforcement learning framework (MeSH), in which each low-level sub-policy focuses on a specific sub-task respectively and high-level policy automatically learns to utilize low-level sub-policies through meta-gradients.

Hierarchical Reinforcement Learning Meta Reinforcement Learning +2

Dual Bipartite Graph Learning: A General Approach for Domain Adaptive Object Detection

no code implementations ICCV 2021 Chaoqi Chen, Jiongcheng Li, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu

Domain Adaptive Object Detection (DAOD) relieves the reliance on large-scale annotated data by transferring the knowledge learned from a labeled source domain to a new unlabeled target domain.

Domain Adaptation Graph Learning +2

Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding

no code implementations10 Dec 2020 Liyan Sun, Chenxin Li, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu

Motivated by the spatial consistency and regularity in medical images, we developed an efficient global correlation module to capture the correlation between a support and query image and incorporate it into the deep network called global correlation network.

Clustering Image Segmentation +2

Adaptive noise imitation for image denoising

no code implementations30 Nov 2020 Huangxing Lin, Yihong Zhuang, Yue Huang, Xinghao Ding, Yizhou Yu, Xiaoqing Liu, John Paisley

Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.

Image Denoising

A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision

1 code implementation23 Oct 2020 Liyan Sun, Jianxiong Wu, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu

We further proposed a localization branch realized via an aggregation of high-level features in a deep decoder to predict locations of organ and lesion, which enriches student segmentor with precise localization information.

Image Segmentation Lesion Segmentation +2

Hard Class Rectification for Domain Adaptation

1 code implementation8 Aug 2020 Yunlong Zhang, Changxing Jing, Huangxing Lin, Chaoqi Chen, Yue Huang, Xinghao Ding, Yang Zou

Second, we further consider that the predictions of target samples belonging to the hard class are vulnerable to perturbations.

Semi-supervised Domain Adaptation Unsupervised Domain Adaptation

Harmonizing Transferability and Discriminability for Adapting Object Detectors

1 code implementation CVPR 2020 Chaoqi Chen, Zebiao Zheng, Xinghao Ding, Yue Huang, Qi Dou

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline.

Object object-detection +1

Noise2Blur: Online Noise Extraction and Denoising

no code implementations3 Dec 2019 Huangxing Lin, Weihong Zeng, Xinghao Ding, Xueyang Fu, Yue Huang, John Paisley

Using the new image pair, the denoising network learns to generate clean and high-quality images from noisy observations.

Image Denoising

Learning Rate Dropout

1 code implementation30 Nov 2019 Huangxing Lin, Weihong Zeng, Xinghao Ding, Yue Huang, Chenxi Huang, John Paisley

The uncertainty of the descent path helps the model avoid saddle points and bad local minima.

Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network

no code implementations28 Oct 2019 Jiexiang Wang, Hongyu Huang, Chaoqi Chen, Wenao Ma, Yue Huang, Xinghao Ding

Automatic and accurate segmentation of the ventricles and myocardium from multi-sequence cardiac MRI (CMR) is crucial for the diagnosis and treatment management for patients suffering from myocardial infarction (MI).

Domain Adaptation Management +1

Unsupervised Adversarial Graph Alignment with Graph Embedding

no code implementations1 Jul 2019 Chaoqi Chen, Weiping Xie, Tingyang Xu, Yu Rong, Wenbing Huang, Xinghao Ding, Yue Huang, Junzhou Huang

In this paper, we propose an Unsupervised Adversarial Graph Alignment (UAGA) framework to learn a cross-graph alignment between two embedding spaces of different graphs in a fully unsupervised fashion (\emph{i. e.,} no existing anchor links and no users' personal profile or attribute information is available).

Attribute Graph Embedding +1

Rain O'er Me: Synthesizing real rain to derain with data distillation

no code implementations9 Apr 2019 Huangxing Lin, Yanlong Li, Xinghao Ding, Weihong Zeng, Yue Huang, John Paisley

We present a supervised technique for learning to remove rain from images without using synthetic rain software.

Rain Removal

A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal

no code implementations24 Nov 2018 Huangxing Lin, Xueyang Fu, Changxing Jing, Xinghao Ding, Yue Huang

Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens.

Rain Removal

A Deep Tree-Structured Fusion Model for Single Image Deraining

no code implementations21 Nov 2018 Xueyang Fu, Qi Qi, Yue Huang, Xinghao Ding, Feng Wu, John Paisley

We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem.

Single Image Deraining

An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection

no code implementations25 Oct 2018 Liyan Sun, Jiexiang Wang, Yue Huang, Xinghao Ding, Hayit Greenspan, John Paisley

Being able to provide a "normal" counterpart to a medical image can provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments.

Data Augmentation General Classification +6

Lightweight Pyramid Networks for Image Deraining

no code implementations16 May 2018 Xueyang Fu, Borong Liang, Yue Huang, Xinghao Ding, John Paisley

In this paper, we propose a lightweight pyramid of networks (LPNet) for single image deraining.

8k Single Image Deraining

A Deeply-Recursive Convolutional Network for Crowd Counting

no code implementations15 May 2018 Xinghao Ding, Zhirui Lin, Fujin He, Yu Wang, Yue Huang

The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning.

Crowd Counting

A Deep Information Sharing Network for Multi-contrast Compressed Sensing MRI Reconstruction

no code implementations10 Apr 2018 Liyan Sun, Zhiwen Fan, Yue Huang, Xinghao Ding, John Paisley

In multi-contrast magnetic resonance imaging (MRI), compressed sensing theory can accelerate imaging by sampling fewer measurements within each contrast.

MRI Reconstruction

A Divide-and-Conquer Approach to Compressed Sensing MRI

no code implementations27 Mar 2018 Liyan Sun, Zhiwen Fan, Xinghao Ding, Congbo Cai, Yue Huang, John Paisley

Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires.

A Deep Error Correction Network for Compressed Sensing MRI

no code implementations23 Mar 2018 Liyan Sun, Zhiwen Fan, Yue Huang, Xinghao Ding, John Paisley

Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction.

MRI Reconstruction

PanNet: A Deep Network Architecture for Pan-Sharpening

no code implementations ICCV 2017 Junfeng Yang, Xueyang Fu, Yuwen Hu, Yue Huang, Xinghao Ding, John Paisley

We incorporate domain-specific knowledge to design our PanNet architecture by focusing on the two aims of the pan-sharpening problem: spectral and spatial preservation.

Removing Rain From Single Images via a Deep Detail Network

no code implementations CVPR 2017 Xueyang Fu, Jia-Bin Huang, Delu Zeng, Yue Huang, Xinghao Ding, John Paisley

We propose a new deep network architecture for removing rain streaks from individual images based on the deep convolutional neural network (CNN).

Denoising Rain Removal

A Weighted Variational Model for Simultaneous Reflectance and Illumination Estimation

no code implementations CVPR 2016 Xueyang Fu, Delu Zeng, Yue Huang, Xiao-Ping Zhang, Xinghao Ding

We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image.

Saliency Detection with Spaces of Background-based Distribution

no code implementations17 Mar 2016 Tong Zhao, Lin Li, Xinghao Ding, Yue Huang, Delu Zeng

In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background.

Saliency Detection

Pan-Sharpening With a Hyper-Laplacian Penalty

no code implementations ICCV 2015 Yiyong Jiang, Xinghao Ding, Delu Zeng, Yue Huang, John Paisley

Our objective incorporates the L1/2-norm in a way that can leverage recent computationally efficient methods, and L1 for which the alternating direction method of multipliers can be used.

Computational Efficiency

HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks

no code implementations28 Sep 2013 Chuan Shi, Xiangnan Kong, Yue Huang, Philip S. Yu, Bin Wu

Similarity search is an important function in many applications, which usually focuses on measuring the similarity between objects with the same type.

Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI

no code implementations12 Feb 2013 Yue Huang, John Paisley, Qin Lin, Xinghao Ding, Xueyang Fu, Xiao-Ping Zhang

The size of the dictionary and the patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables.

Denoising Dictionary Learning +2

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