Search Results for author: Hui Xue

Found 51 papers, 20 papers with code

PIAT: Parameter Interpolation based Adversarial Training for Image Classification

no code implementations24 Mar 2023 Kun He, Xin Liu, Yichen Yang, Zhou Qin, Weigao Wen, Hui Xue, John E. Hopcroft

Besides, we suggest to use the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the clean and adversarial examples.

Image Classification

To Make Yourself Invisible with Adversarial Semantic Contours

no code implementations1 Mar 2023 Yichi Zhang, Zijian Zhu, Hang Su, Jun Zhu, Shibao Zheng, Yuan He, Hui Xue

In this paper, we propose Adversarial Semantic Contour (ASC), an MAP estimate of a Bayesian formulation of sparse attack with a deceived prior of object contour.

Autonomous Driving object-detection +1

A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking

no code implementations28 Feb 2023 Chang Liu, Yinpeng Dong, Wenzhao Xiang, Xiao Yang, Hang Su, Jun Zhu, Yuefeng Chen, Yuan He, Hui Xue, Shibao Zheng

In our benchmark, we evaluate the robustness of 55 typical deep learning models on ImageNet with diverse architectures (e. g., CNNs, Transformers) and learning algorithms (e. g., normal supervised training, pre-training, adversarial training) under numerous adversarial attacks and out-of-distribution (OOD) datasets.

Adversarial Robustness Benchmarking +2

Improving Model Generalization by On-manifold Adversarial Augmentation in the Frequency Domain

no code implementations28 Feb 2023 Chang Liu, Wenzhao Xiang, Yuan He, Hui Xue, Shibao Zheng, Hang Su

To address this issue, we proposed a novel method of Augmenting data with Adversarial examples via a Wavelet module (AdvWavAug), an on-manifold adversarial data augmentation technique that is simple to implement.

Data Augmentation

Improving Scene Text Image Super-Resolution via Dual Prior Modulation Network

1 code implementation21 Feb 2023 Shipeng Zhu, Zuoyan Zhao, Pengfei Fang, Hui Xue

Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, and the resulting images will significantly affect the performance of downstream tasks.

Image Super-Resolution

Rethinking Out-of-Distribution Detection From a Human-Centric Perspective

no code implementations30 Nov 2022 Yao Zhu, Yuefeng Chen, Xiaodan Li, Rong Zhang, Hui Xue, Xiang Tian, Rongxin Jiang, Bolun Zheng, Yaowu Chen

Additionally, our experiments demonstrate that model selection is non-trivial for OOD detection and should be considered as an integral of the proposed method, which differs from the claim in existing works that proposed methods are universal across different models.

Model Selection Out-of-Distribution Detection +1

Context-Aware Robust Fine-Tuning

no code implementations29 Nov 2022 Xiaofeng Mao, Yuefeng Chen, Xiaojun Jia, Rong Zhang, Hui Xue, Zhao Li

Contrastive Language-Image Pre-trained (CLIP) models have zero-shot ability of classifying an image belonging to "[CLASS]" by using similarity between the image and the prompt sentence "a [CONTEXT] of [CLASS]".

 Ranked #1 on Domain Generalization on DomainNet (using extra training data)

Domain Generalization

RoChBert: Towards Robust BERT Fine-tuning for Chinese

1 code implementation28 Oct 2022 Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.

Data Augmentation Language Modelling

Boosting Out-of-distribution Detection with Typical Features

1 code implementation9 Oct 2022 Yao Zhu, Yuefeng Chen, Chuanlong Xie, Xiaodan Li, Rong Zhang, Hui Xue, Xiang Tian, Bolun Zheng, Yaowu Chen

Out-of-distribution (OOD) detection is a critical task for ensuring the reliability and safety of deep neural networks in real-world scenarios.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

D^2ETR: Decoder-Only DETR with Computationally Efficient Cross-Scale Attention

no code implementations2 Mar 2022 Junyu Lin, Xiaofeng Mao, Yuefeng Chen, Lei Xu, Yuan He, Hui Xue

DETR is the first fully end-to-end detector that predicts a final set of predictions without post-processing.

Multi-View Fusion Transformer for Sensor-Based Human Activity Recognition

no code implementations16 Feb 2022 Yimu Wang, Kun Yu, Yan Wang, Hui Xue

In this paper, to extract a better feature for advancing the performance, we propose a novel method, namely multi-view fusion transformer (MVFT) along with a novel attention mechanism.

Human Activity Recognition Time Series Analysis

Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains

2 code implementations ICLR 2022 Qilong Zhang, Xiaodan Li, Yuefeng Chen, Jingkuan Song, Lianli Gao, Yuan He, Hui Xue

Notably, our methods outperform state-of-the-art approaches by up to 7. 71\% (towards coarse-grained domains) and 25. 91\% (towards fine-grained domains) on average.

An Automated Question-Answering Framework Based on Evolution Algorithm

no code implementations26 Jan 2022 Sinan Tan, Hui Xue, Qiyu Ren, Huaping Liu, Jing Bai

Our framework is based on an innovative evolution algorithm, which is stable and suitable for multiple dataset scenario.

Question Answering

DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework

no code implementations21 Jul 2021 Haiwen Hong, Xuan Jin, Yin Zhang, Yunqing Hu, Jingfeng Zhang, Yuan He, Hui Xue

In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of Dual-Router, MWF-Layer, experts and expert fusion unit.

RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition

no code implementations17 Jul 2021 Yunqing Hu, Xuan Jin, Yin Zhang, Haiwen Hong, Jingfeng Zhang, Yuan He, Hui Xue

We propose the recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi-scale manner.

Fine-Grained Image Classification Fine-Grained Image Recognition

Towards Robust Vision Transformer

2 code implementations CVPR 2022 Xiaofeng Mao, Gege Qi, Yuefeng Chen, Xiaodan Li, Ranjie Duan, Shaokai Ye, Yuan He, Hui Xue

By using and combining robust components as building blocks of ViTs, we propose Robust Vision Transformer (RVT), which is a new vision transformer and has superior performance with strong robustness.

Domain Generalization Image Classification +1

QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval

no code implementations CVPR 2021 Xiaodan Li, Jinfeng Li, Yuefeng Chen, Shaokai Ye, Yuan He, Shuhui Wang, Hang Su, Hui Xue

Comprehensive experiments show that the proposed attack achieves a high attack success rate with few queries against the image retrieval systems under the black-box setting.

Image Classification Image Retrieval +1

Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation

no code implementations23 Feb 2021 Jinfeng Li, Tianyu Du, Xiangyu Liu, Rong Zhang, Hui Xue, Shouling Ji

Extensive experiments on two real-world tasks show that AdvGraph exhibits better performance compared with previous work: (i) effective - it significantly strengthens the model robustness even under the adaptive attacks setting without negative impact on model performance over legitimate input; (ii) generic - its key component, i. e., the representation of connotative adversarial knowledge is task-agnostic, which can be reused in any Chinese-based NLP models without retraining; and (iii) efficient - it is a light-weight defense with sub-linear computational complexity, which can guarantee the efficiency required in practical scenarios.

Cut out the annotator, keep the cutout: better segmentation with weak supervision

no code implementations ICLR 2021 Sarah Hooper, Michael Wornow, Ying Hang Seah, Peter Kellman, Hui Xue, Frederic Sala, Curtis Langlotz, Christopher Re

We propose a framework that fuses limited label learning and weak supervision for segmentation tasks, enabling users to train high-performing segmentation CNNs with very few hand-labeled training points.

Data Augmentation Few-Shot Learning +3

The Open Brands Dataset: Unified brand detection and recognition at scale

no code implementations14 Dec 2020 Xuan Jin, Wei Su, Rong Zhang, Yuan He, Hui Xue

To the best of our knowledge, it is the largest dataset for brand detection and recognition with rich annotations.

object-detection Object Detection

Composite Adversarial Attacks

1 code implementation10 Dec 2020 Xiaofeng Mao, Yuefeng Chen, Shuhui Wang, Hang Su, Yuan He, Hui Xue

Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness.

Adversarial Attack Adversarial Robustness

Landmark detection in Cardiac Magnetic Resonance Imaging Using A Convolutional Neural Network

1 code implementation14 Aug 2020 Hui Xue, Jessica Artico, Marianna Fontana, James C. Moon, Rhodri H. Davies, Peter Kellman

Conclusions: This study developed, validated and deployed a CNN solution for robust landmark detection in both long and short-axis CMR images for cine, LGE and T1 mapping sequences, with the accuracy comparable to the inter-operator variation.

Sharp Multiple Instance Learning for DeepFake Video Detection

no code implementations11 Aug 2020 Xiaodan Li, Yining Lang, Yuefeng Chen, Xiaofeng Mao, Yuan He, Shuhui Wang, Hui Xue, Quan Lu

A sharp MIL (S-MIL) is proposed which builds direct mapping from instance embeddings to bag prediction, rather than from instance embeddings to instance prediction and then to bag prediction in traditional MIL.

Face Swapping Multiple Instance Learning

MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks

no code implementations3 Jul 2020 Yusi Zhang, Chuanjie Liu, Angen Luo, Hui Xue, Xuan Shan, Yuxiang Luo, Yiqian Xia, Yuanchi Yan, Haidong Wang

The common framework is to train two encoding models based on neural embedding which learn the distributed representations of queries and documents separately and match them in the latent semantic space.

Graph Attention Retrieval

GAP++: Learning to generate target-conditioned adversarial examples

no code implementations9 Jun 2020 Xiaofeng Mao, Yuefeng Chen, Yuhong Li, Yuan He, Hui Xue

Different from previous single-target attack models, our model can conduct target-conditioned attacks by learning the relations of attack target and the semantics in image.

Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling

1 code implementation29 May 2020 Wenwu Ye, Jin Yao, Hui Xue, Yi Li

Localizing thoracic diseases on chest X-ray plays a critical role in clinical practices such as diagnosis and treatment planning.

Towards Face Encryption by Generating Adversarial Identity Masks

1 code implementation ICCV 2021 Xiao Yang, Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu, Yuefeng Chen, Hui Xue

As billions of personal data being shared through social media and network, the data privacy and security have drawn an increasing attention.

Face Recognition

Deeper Insights into Weight Sharing in Neural Architecture Search

1 code implementation6 Jan 2020 Yuge Zhang, Zejun Lin, Junyang Jiang, Quanlu Zhang, Yujing Wang, Hui Xue, Chen Zhang, Yaming Yang

With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention.

Neural Architecture Search

Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift

no code implementations18 Dec 2019 Da Chen, Yong-Liang Yang, Zunlei Feng, Xiang Wu, Mingli Song, Wenbin Li, Yuan He, Hui Xue, Feng Mao

This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set.

Few-Shot Image Classification General Classification +1

AdvKnn: Adversarial Attacks On K-Nearest Neighbor Classifiers With Approximate Gradients

1 code implementation15 Nov 2019 Xiaodan Li, Yuefeng Chen, Yuan He, Hui Xue

Deep neural networks have been shown to be vulnerable to adversarial examples---maliciously crafted examples that can trigger the target model to misbehave by adding imperceptible perturbations.

Adversarial Robustness

Self-supervised Adversarial Training

1 code implementation15 Nov 2019 Kejiang Chen, Hang Zhou, Yuefeng Chen, Xiaofeng Mao, Yuhong Li, Yuan He, Hui Xue, Weiming Zhang, Nenghai Yu

Recent work has demonstrated that neural networks are vulnerable to adversarial examples.

Self-Supervised Learning

Learning To Characterize Adversarial Subspaces

no code implementations15 Nov 2019 Xiaofeng Mao, Yuefeng Chen, Yuhong Li, Yuan He, Hui Xue

To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of \textit{adversarial subspaces} where adversarial examples lie.

Self-Supervised Learning For Few-Shot Image Classification

3 code implementations14 Nov 2019 Da Chen, Yuefeng Chen, Yuhong Li, Feng Mao, Yuan He, Hui Xue

In this paper, we proposed to train a more generalized embedding network with self-supervised learning (SSL) which can provide robust representation for downstream tasks by learning from the data itself.

Classification cross-domain few-shot learning +3

Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning

no code implementations2 Nov 2019 Hui Xue, Rhodri Davies, Louis AE Brown, Kristopher D Knott, Tushar Kotecha, Marianna Fontana, Sven Plein, James C. Moon, Peter Kellman

This solution was integrated on the MR scanner, enabling 'one-click' analysis and reporting of myocardial blood flow.

DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition

no code implementations10 Oct 2019 Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang, Zhichao Han, Bo Li, Wei Min, Xi Rao, Hansheng Ren, Yinan Shan, Yingxia Shao, Yujie Wang, Fan Wu, Hui Xue, Yaming Yang, Zitao Zhang, Yang Zhao, Shuai Zhang, Yujing Wang, Bin Cui, Ce Zhang

Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.

Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network

no code implementations2 Jun 2019 Feng Mao, Xiang Wu, Hui Xue, Rong Zhang

However, the video length is usually long, and there are hierarchical relationships between frames across events in the video, the performance of RNN based models are decreased.

General Classification Video Classification +1

Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks

1 code implementation18 Mar 2019 Xiaofeng Mao, Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue

The task of Language-Based Image Editing (LBIE) aims at generating a target image by editing the source image based on the given language description.

Deep Features Analysis with Attention Networks

no code implementations20 Jan 2019 Shipeng Xie, Da Chen, Rong Zhang, Hui Xue

Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc.

Classification General Classification +3

Ranking Responses Oriented to Conversational Relevance in Chat-bots

no code implementations COLING 2016 Bowen Wu, Baoxun Wang, Hui Xue

For automatic chatting systems, it is indeed a great challenge to reply the given query considering the conversation history, rather than based on the query only.

Logistic Boosting Regression for Label Distribution Learning

no code implementations CVPR 2016 Chao Xing, Xin Geng, Hui Xue

In order to learn this general model family, this paper uses a method called Logistic Boosting Regression (LogitBoost) which can be seen as an additive weighted function regression from the statistical viewpoint.

Age Estimation Facial Expression Recognition (FER) +2

LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks

no code implementations8 Nov 2015 Steven C. H. Hoi, Xiongwei Wu, Hantang Liu, Yue Wu, Huiqiong Wang, Hui Xue, Qiang Wu

In this paper, we introduce "LOGO-Net", a large-scale logo image database for logo detection and brand recognition from real-world product images.

Logo Recognition object-detection +1

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