Search Results for author: Yuan He

Found 64 papers, 28 papers with code

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

Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking

no code implementations14 Feb 2023 Hang Dong, Jiaoyan Chen, Yuan He, Yinan Liu, Ian Horrocks

Discovering entity mentions that are out of a Knowledge Base (KB) from texts plays a critical role in KB maintenance, but has not yet been fully explored.

Entity Linking

Language Model Analysis for Ontology Subsumption Inference

1 code implementation14 Feb 2023 Yuan He, Jiaoyan Chen, Ernesto Jiménez-Ruiz, Hang Dong, Ian Horrocks

Pre-trained language models (LMs) have made significant advances in various Natural Language Processing (NLP) domains, but it is unclear to what extent they can infer formal semantics in ontologies, which are often used to represent conceptual knowledge and serve as the schema of data graphs.

Language Modelling Natural Language Inference +1

OpenAUC: Towards AUC-Oriented Open-Set Recognition

1 code implementation22 Oct 2022 Zitai Wang, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, Qingming Huang

In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden's index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction.

Open Set Learning

Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective

2 code implementations9 Oct 2022 Yao Zhu, Yuefeng Chen, Xiaodan Li, Kejiang Chen, Yuan He, Xiang Tian, Bolun Zheng, Yaowu Chen, Qingming Huang

We conduct comprehensive transferable attacks against multiple DNNs to demonstrate the effectiveness of the proposed method.

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

no code implementations30 Sep 2022 Shilong Bao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, Qingming Huang

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering.

Collaborative Filtering Metric Learning +1

MaxMatch: Semi-Supervised Learning with Worst-Case Consistency

no code implementations26 Sep 2022 Yangbangyan Jiang, Xiaodan Li, Yuefeng Chen, Yuan He, Qianqian Xu, Zhiyong Yang, Xiaochun Cao, Qingming Huang

In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL).

Optimizing Partial Area Under the Top-k Curve: Theory and Practice

no code implementations3 Sep 2022 Zitai Wang, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, Qingming Huang

Finally, the experimental results on four benchmark datasets validate the effectiveness of our proposed framework.

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems

no code implementations24 Jun 2022 Wenzheng Hou, Qianqian Xu, Zhiyong Yang, Shilong Bao, Yuan He, Qingming Huang

Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem.

Optimizing Two-way Partial AUC with an End-to-end Framework

1 code implementation23 Jun 2022 Zhiyong Yang, Qianqian Xu, Shilong Bao, Yuan He, Xiaochun Cao, Qingming Huang

The critical challenge along this course lies in the difficulty of performing gradient-based optimization with end-to-end stochastic training, even with a proper choice of surrogate loss.

Machine Learning-Friendly Biomedical Datasets for Equivalence and Subsumption Ontology Matching

2 code implementations6 May 2022 Yuan He, Jiaoyan Chen, Hang Dong, Ernesto Jiménez-Ruiz, Ali Hadian, Ian Horrocks

Ontology Matching (OM) plays an important role in many domains such as bioinformatics and the Semantic Web, and its research is becoming increasingly popular, especially with the application of machine learning (ML) techniques.

Ontology Matching

RMGN: A Regional Mask Guided Network for Parser-free Virtual Try-on

1 code implementation24 Apr 2022 Chao Lin, Zhao Li, Sheng Zhou, Shichang Hu, Jialun Zhang, Linhao Luo, Jiarun Zhang, Longtao Huang, Yuan He

Virtual try-on(VTON) aims at fitting target clothes to reference person images, which is widely adopted in e-commerce. Existing VTON approaches can be narrowly categorized into Parser-Based(PB) and Parser-Free(PF) by whether relying on the parser information to mask the persons' clothes and synthesize try-on images.

Virtual Try-on

Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition

no code implementations22 Apr 2022 Yunqing Hu, Xuan Jin, Yin Zhang, Haiwen Hong, Jingfeng Zhang, Feihu Yan, Yuan He, Hui Xue

Finally, we propose a weakly supervised object localization-based approach to extract multi-scale local features, to form a multi-view pipeline.

Weakly-Supervised Object Localization

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.

Contextual Semantic Embeddings for Ontology Subsumption Prediction

2 code implementations20 Feb 2022 Jiaoyan Chen, Yuan He, Yuxia Geng, Ernesto Jimenez-Ruiz, Hang Dong, Ian Horrocks

Automating ontology construction and curation is an important but challenging task in knowledge engineering and artificial intelligence.

Knowledge Graph Embeddings Language Modelling +1

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.

Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey

no code implementations18 Dec 2021 Jiaoyan Chen, Yuxia Geng, Zhuo Chen, Jeff Z. Pan, Yuan He, Wen Zhang, Ian Horrocks, Huajun Chen

Machine learning especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for supervision.

Data Augmentation Few-Shot Learning +10

BERTMap: A BERT-based Ontology Alignment System

1 code implementation5 Dec 2021 Yuan He, Jiaoyan Chen, Denvar Antonyrajah, Ian Horrocks

Ontology alignment (a. k. a ontology matching (OM)) plays a critical role in knowledge integration.

Feature Engineering Ontology Matching +1

When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking

no code implementations NeurIPS 2021 Peisong Wen, Qianqian Xu, Zhiyong Yang, Yuan He, Qingming Huang

To leverage high performance under low FPRs, we consider an alternative metric for multipartite ranking evaluating the True Positive Rate (TPR) at a given FPR, denoted as TPR@FPR.

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

no code implementations29 Sep 2021 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.

Prior-Guided Deep Interference Mitigation for FMCW Radars

no code implementations30 Aug 2021 JianPing Wang, Runlong Li, Yuan He, Yang Yang

The effectiveness and accuracy of our proposed complex-valued fully convolutional network (CV-FCN) based interference mitigation approach are verified and analyzed through both simulated and measured radar signals.

AdvDrop: Adversarial Attack to DNNs by Dropping Information

1 code implementation ICCV 2021 Ranjie Duan, Yuefeng Chen, Dantong Niu, Yun Yang, A. K. Qin, Yuan He

Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e. g. cartoon.

Adversarial Attack Adversarial Robustness

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

Monocular 3D Object Detection: An Extrinsic Parameter Free Approach

no code implementations CVPR 2021 Yunsong Zhou, Yuan He, Hongzi Zhu, Cheng Wang, Hongyang Li, Qinhong Jiang

Due to the lack of insight in industrial application, existing methods on open datasets neglect the camera pose information, which inevitably results in the detector being susceptible to camera extrinsic parameters.

Ranked #5 on Monocular 3D Object Detection on KITTI Cars Moderate (using extra training data)

Autonomous Driving Monocular 3D Object Detection +1

Sketch, Ground, and Refine: Top-Down Dense Video Captioning

no code implementations CVPR 2021 Chaorui Deng, ShiZhe Chen, Da Chen, Yuan He, Qi Wu

The dense video captioning task aims to detect and describe a sequence of events in a video for detailed and coherent storytelling.

Dense Video Captioning

When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking

no code implementations NeurIPS 2021 Peisong Wen, Qianqian Xu, Zhiyong Yang, Yuan He, Qingming Huang

To leverage high performance under low FPRs, we consider an alternative metric for multipartite ranking evaluating the True Positive Rate (TPR) at a given FPR, denoted as TPR@FPR.

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

Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning

1 code implementation6 Apr 2021 Jianfeng Dong, Zhe Ma, Xiaofeng Mao, Xun Yang, Yuan He, Richang Hong, Shouling Ji

In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute between fashion items.

Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink

1 code implementation CVPR 2021 Ranjie Duan, Xiaofeng Mao, A. K. Qin, Yun Yang, Yuefeng Chen, Shaokai Ye, Yuan He

Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted from some physical source as adversarial attacker on DNNs in a real-world scenario.

Adversarial Attack

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

Hierarchical Similarity Learning for Language-based Product Image Retrieval

1 code implementation18 Feb 2021 Zhe Ma, Fenghao Liu, Jianfeng Dong, Xiaoye Qu, Yuan He, Shouling Ji

In this paper, we focus on the cross-modal similarity measurement, and propose a novel Hierarchical Similarity Learning (HSL) network.

Image Retrieval Retrieval +1

$\rm ^{83}Rb$/$\rm ^{83m}Kr$ production and cross-section measurement with 3.4 MeV and 20 MeV proton beams

no code implementations4 Feb 2021 Dan Zhang, Jingkai Xia, YiFan Li, Jingtao You, Yao Li, Changbo Fu, Jianglai Liu, Ning Zhou, Jie Bao, Huan Jia, Chenzhang Yuan, Yuan He, Weixing Xiong, Mengyun Guan

$\rm ^{83m}Kr$, with a short lifetime, is an ideal calibration source for liquid xenon or liquid argon detectors.

Nuclear Experiment Instrumentation and Detectors

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

Heuristic Domain Adaptation

1 code implementation NeurIPS 2020 Shuhao Cui, Xuan Jin, Shuhui Wang, Yuan He, Qingming Huang

In visual domain adaptation (DA), separating the domain-specific characteristics from the domain-invariant representations is an ill-posed problem.

Domain Adaptation

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

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.

Robust Generative Adversarial Network

no code implementations ICLR 2020 Shufei Zhang, Zhuang Qian, Kai-Zhu Huang, Jimin Xiao, Yuan He

Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations.

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

Progressive Relation Learning for Group Activity Recognition

no code implementations CVPR 2020 Guyue Hu, Bo Cui, Yuan He, Shan Yu

Another relation-gating (RG) agent in continuous action space adjusts the high-level semantic graph to pay more attention to group-relevant relations.

Group Activity Recognition

Leveraging Deep Learning to Improve the Performance Predictability of Cloud Microservices

no code implementations2 May 2019 Yu Gan, Yanqi Zhang, Kelvin Hu, Dailun Cheng, Yuan He, Meghna Pancholi, Christina Delimitrou

We show that Seer correctly anticipates QoS violations 91% of the time, and avoids the QoS violation to begin with in 84% of cases.

Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar

no code implementations Neurocomputing 2019 Hao Du, Tian Jin, Yuan He, Yongping Song, Yongpeng Dai

In this work, we propose a neural network architecture, namely segmented convolutional gated recurrent neural network (SCGRNN), to recognize human activities based on micro-Doppler spectrograms measured by the ultra-wideband radar.

Human Activity Recognition RF-based Action Recognition +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.

Graph Neural Networks for Social Recommendation

7 code implementations19 Feb 2019 Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, Dawei Yin

These advantages of GNNs provide great potential to advance social recommendation since data in social recommender systems can be represented as user-user social graph and user-item graph; and learning latent factors of users and items is the key.

Ranked #3 on Recommendation Systems on Epinions (using extra training data)

Recommendation Systems

A Neural Network Aided Approach for LDPC Coded DCO-OFDM with Clipping Distortion

no code implementations4 Sep 2018 Yuan He, Ming Jiang, Chunming Zhao

In this paper, a neural network-aided bit-interleaved coded modulation (NN-BICM) receiver is designed to mitigate the nonlinear clipping distortion in the LDPC coded direct currentbiased optical orthogonal frequency division multiplexing (DCOOFDM) systems.

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