Search Results for author: Shu-Tao Xia

Found 114 papers, 64 papers with code

Backdoor Learning: A Survey

1 code implementation17 Jul 2020 Yiming Li, Yong Jiang, Zhifeng Li, Shu-Tao Xia

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by attacker-specified triggers.

Backdoor Attack Data Poisoning

Adversarial Weight Perturbation Helps Robust Generalization

3 code implementations NeurIPS 2020 Dongxian Wu, Shu-Tao Xia, Yisen Wang

The study on improving the robustness of deep neural networks against adversarial examples grows rapidly in recent years.

Adversarial Robustness

BackdoorBox: A Python Toolbox for Backdoor Learning

1 code implementation1 Feb 2023 Yiming Li, Mengxi Ya, Yang Bai, Yong Jiang, Shu-Tao Xia

Third-party resources ($e. g.$, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a new training-phase threat.

MambaIR: A Simple Baseline for Image Restoration with State-Space Model

1 code implementation23 Feb 2024 Hang Guo, Jinmin Li, Tao Dai, Zhihao Ouyang, Xudong Ren, Shu-Tao Xia

In this way, our MambaIR takes advantage of the local pixel similarity and reduces the channel redundancy.

Image Restoration

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

3 code implementations ICLR 2020 Dongxian Wu, Yisen Wang, Shu-Tao Xia, James Bailey, Xingjun Ma

We find that using more gradients from the skip connections rather than the residual modules according to a decay factor, allows one to craft adversarial examples with high transferability.

TokenPose: Learning Keypoint Tokens for Human Pose Estimation

1 code implementation ICCV 2021 YanJie Li, Shoukui Zhang, Zhicheng Wang, Sen yang, Wankou Yang, Shu-Tao Xia, Erjin Zhou

Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints.

Pose Estimation

Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer

1 code implementation5 Jul 2022 Sunan He, Taian Guo, Tao Dai, Ruizhi Qiao, Bo Ren, Shu-Tao Xia

Specifically, our method exploits multi-modal knowledge of image-text pairs based on a vision and language pre-training (VLP) model.

Image-text matching Knowledge Distillation +7

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses

1 code implementation6 Feb 2024 Hao Fang, Yixiang Qiu, Hongyao Yu, Wenbo Yu, Jiawei Kong, Baoli Chong, Bin Chen, Xuan Wang, Shu-Tao Xia

Model Inversion (MI) attacks aim to disclose private information about the training data by abusing access to the pre-trained models.

Improving Adversarial Robustness via Channel-wise Activation Suppressing

1 code implementation ICLR 2021 Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Xingjun Ma, Yisen Wang

The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs).

Adversarial Robustness

Learning Transferable Spatiotemporal Representations from Natural Script Knowledge

1 code implementation CVPR 2023 Ziyun Zeng, Yuying Ge, Xihui Liu, Bin Chen, Ping Luo, Shu-Tao Xia, Yixiao Ge

Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years.

Descriptive Representation Learning +1

TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale

1 code implementation23 May 2023 Ziyun Zeng, Yixiao Ge, Zhan Tong, Xihui Liu, Shu-Tao Xia, Ying Shan

We argue that tuning a text encoder end-to-end, as done in previous work, is suboptimal since it may overfit in terms of styles, thereby losing its original generalization ability to capture the semantics of various language registers.

Representation Learning

Improving Vision Transformers by Revisiting High-frequency Components

1 code implementation3 Apr 2022 Jiawang Bai, Li Yuan, Shu-Tao Xia, Shuicheng Yan, Zhifeng Li, Wei Liu

Inspired by this finding, we first investigate the effects of existing techniques for improving ViT models from a new frequency perspective, and find that the success of some techniques (e. g., RandAugment) can be attributed to the better usage of the high-frequency components.

Domain Generalization Image Classification +1

Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement

1 code implementation19 Jul 2023 Hang Guo, Tao Dai, Guanghao Meng, Shu-Tao Xia

Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success.

Image Super-Resolution LEMMA +1

Backdoor Defense via Adaptively Splitting Poisoned Dataset

1 code implementation CVPR 2023 Kuofeng Gao, Yang Bai, Jindong Gu, Yong Yang, Shu-Tao Xia

With the split clean data pool and polluted data pool, ASD successfully defends against backdoor attacks during training.

backdoor defense

Contrastive Quantization with Code Memory for Unsupervised Image Retrieval

1 code implementation11 Sep 2021 Jinpeng Wang, Ziyun Zeng, Bin Chen, Tao Dai, Shu-Tao Xia

The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems.

Contrastive Learning Deep Hashing +1

Defending against Model Stealing via Verifying Embedded External Features

1 code implementation ICML Workshop AML 2021 Yiming Li, Linghui Zhu, Xiaojun Jia, Yong Jiang, Shu-Tao Xia, Xiaochun Cao

In this paper, we explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified \emph{external features}.

Style Transfer

Targeted Attack for Deep Hashing based Retrieval

2 code implementations ECCV 2020 Jiawang Bai, Bin Chen, Yiming Li, Dongxian Wu, Weiwei Guo, Shu-Tao Xia, En-hui Yang

In this paper, we propose a novel method, dubbed deep hashing targeted attack (DHTA), to study the targeted attack on such retrieval.

Deep Hashing Image Retrieval +1

Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters

1 code implementation ECCV 2020 Haoyu Liang, Zhihao Ouyang, Yuyuan Zeng, Hang Su, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang

Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model.

Object Localization

GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization

1 code implementation ICCV 2023 Hao Fang, Bin Chen, Xuan Wang, Zhi Wang, Shu-Tao Xia

Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server.

Federated Learning Image Generation

MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation

1 code implementation22 Aug 2023 Jinpeng Wang, Ziyun Zeng, Yunxiao Wang, Yuting Wang, Xingyu Lu, Tianxiang Li, Jun Yuan, Rui Zhang, Hai-Tao Zheng, Shu-Tao Xia

We propose MISSRec, a multi-modal pre-training and transfer learning framework for SR. On the user side, we design a Transformer-based encoder-decoder model, where the contextual encoder learns to capture the sequence-level multi-modal user interests while a novel interest-aware decoder is developed to grasp item-modality-interest relations for better sequence representation.

Contrastive Learning Sequential Recommendation +1

Backdoor Attack against Speaker Verification

1 code implementation22 Oct 2020 Tongqing Zhai, Yiming Li, Ziqi Zhang, Baoyuan Wu, Yong Jiang, Shu-Tao Xia

We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.

Backdoor Attack Clustering +1

Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders

1 code implementation17 Dec 2023 Yaohua Zha, Huizhen Ji, Jinmin Li, Rongsheng Li, Tao Dai, Bin Chen, Zhi Wang, Shu-Tao Xia

Specifically, to learn more compact features, a share-parameter Transformer encoder is introduced to extract point features from the global and local unmasked patches obtained by global random and local block mask strategies, followed by a specific decoder to reconstruct.

Few-Shot 3D Point Cloud Classification

Stochastic Deep Gaussian Processes over Graphs

1 code implementation NeurIPS 2020 Naiqi Li, Wenjie Li, Jifeng Sun, Yinghua Gao, Yong Jiang, Shu-Tao Xia

In this paper we propose Stochastic Deep Gaussian Processes over Graphs (DGPG), which are deep structure models that learn the mappings between input and output signals in graph domains.

Gaussian Processes Variational Inference

Open-sourced Dataset Protection via Backdoor Watermarking

2 code implementations12 Oct 2020 Yiming Li, Ziqi Zhang, Jiawang Bai, Baoyuan Wu, Yong Jiang, Shu-Tao Xia

Based on the proposed backdoor-based watermarking, we use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model of the benign samples and their correspondingly watermarked samples ($i. e.$, images with trigger) on the target class.

Image Classification

Black-box Dataset Ownership Verification via Backdoor Watermarking

1 code implementation4 Aug 2022 Yiming Li, Mingyan Zhu, Xue Yang, Yong Jiang, Tao Wei, Shu-Tao Xia

The rapid development of DNNs has benefited from the existence of some high-quality datasets ($e. g.$, ImageNet), which allow researchers and developers to easily verify the performance of their methods.

Toward Adversarial Robustness via Semi-supervised Robust Training

1 code implementation16 Mar 2020 Yiming Li, Baoyuan Wu, Yan Feng, Yanbo Fan, Yong Jiang, Zhifeng Li, Shu-Tao Xia

In this work, we propose a novel defense method, the robust training (RT), by jointly minimizing two separated risks ($R_{stand}$ and $R_{rob}$), which is with respect to the benign example and its neighborhoods respectively.

Adversarial Defense Adversarial Robustness

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

2 code implementations ICLR 2021 Jiawang Bai, Baoyuan Wu, Yong Zhang, Yiming Li, Zhifeng Li, Shu-Tao Xia

By utilizing the latest technique in integer programming, we equivalently reformulate this BIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method.

Backdoor Attack

Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval

1 code implementation7 Feb 2022 Jinpeng Wang, Bin Chen, Dongliang Liao, Ziyun Zeng, Gongfu Li, Shu-Tao Xia, Jin Xu

By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels.

Contrastive Learning Quantization +4

AdaptIR: Parameter Efficient Multi-task Adaptation for Pre-trained Image Restoration Models

1 code implementation12 Dec 2023 Hang Guo, Tao Dai, Yuanchao Bai, Bin Chen, Shu-Tao Xia, Zexuan Zhu

Recently, Parameter Efficient Transfer Learning (PETL) offers an efficient alternative solution to full fine-tuning, yet still faces great challenges for pre-trained image restoration models, due to the diversity of different degradations.

Image Denoising Image Restoration +1

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training

1 code implementation ICCV 2023 Jianshuo Dong, Han Qiu, Yiming Li, Tianwei Zhang, Yuanjie Li, Zeqi Lai, Chao Zhang, Shu-Tao Xia

We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.

Towards Effective Image Manipulation Detection with Proposal Contrastive Learning

1 code implementation16 Oct 2022 Yuyuan Zeng, Bowen Zhao, Shanzhao Qiu, Tao Dai, Shu-Tao Xia

Most existing methods mainly focus on extracting global features from tampered images, while neglecting the relationships of local features between tampered and authentic regions within a single tampered image.

Contrastive Learning Image Manipulation +1

One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer

1 code implementation5 Aug 2023 Hang Guo, Tao Dai, Mingyan Zhu, Guanghao Meng, Bin Chen, Zhi Wang, Shu-Tao Xia

Current solutions for low-resolution text recognition (LTR) typically rely on a two-stage pipeline that involves super-resolution as the first stage followed by the second-stage recognition.

Contrastive Learning Knowledge Distillation +2

Improving Query Efficiency of Black-box Adversarial Attack

1 code implementation ECCV 2020 Yang Bai, Yuyuan Zeng, Yong Jiang, Yisen Wang, Shu-Tao Xia, Weiwei Guo

Deep neural networks (DNNs) have demonstrated excellent performance on various tasks, however they are under the risk of adversarial examples that can be easily generated when the target model is accessible to an attacker (white-box setting).

Adversarial Attack

Few-Shot Backdoor Attacks on Visual Object Tracking

1 code implementation ICLR 2022 Yiming Li, Haoxiang Zhong, Xingjun Ma, Yong Jiang, Shu-Tao Xia

Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems.

Autonomous Driving Backdoor Attack +2

Untargeted Backdoor Attack against Object Detection

1 code implementation2 Nov 2022 Chengxiao Luo, Yiming Li, Yong Jiang, Shu-Tao Xia

The backdoored model has promising performance in predicting benign samples, whereas its predictions can be maliciously manipulated by adversaries based on activating its backdoors with pre-defined trigger patterns.

Backdoor Attack Image Classification +4

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

1 code implementation20 Jan 2024 Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, Wei Liu

Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources.

Iterative Learning with Open-set Noisy Labels

1 code implementation CVPR 2018 Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia

We refer to this more complex scenario as the \textbf{open-set noisy label} problem and show that it is nontrivial in order to make accurate predictions.

GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval

1 code implementation8 Oct 2023 Yuting Wang, Jinpeng Wang, Bin Chen, Ziyun Zeng, Shu-Tao Xia

Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead.

Partially Relevant Video Retrieval Retrieval +1

Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips

1 code implementation27 Jul 2022 Jiawang Bai, Kuofeng Gao, Dihong Gong, Shu-Tao Xia, Zhifeng Li, Wei Liu

The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications.

Imperceptible and Robust Backdoor Attack in 3D Point Cloud

1 code implementation17 Aug 2022 Kuofeng Gao, Jiawang Bai, Baoyuan Wu, Mengxi Ya, Shu-Tao Xia

Existing attacks often insert some additional points into the point cloud as the trigger, or utilize a linear transformation (e. g., rotation) to construct the poisoned point cloud.

Backdoor Attack

Towards Robust Model Watermark via Reducing Parametric Vulnerability

1 code implementation ICCV 2023 Guanhao Gan, Yiming Li, Dongxian Wu, Shu-Tao Xia

To protect the copyright of DNNs, backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model by embedding a specific backdoor behavior before releasing it.

$t$-$k$-means: A Robust and Stable $k$-means Variant

1 code implementation17 Jul 2019 Yiming Li, Yang Zhang, Qingtao Tang, Weipeng Huang, Yong Jiang, Shu-Tao Xia

$k$-means algorithm is one of the most classical clustering methods, which has been widely and successfully used in signal processing.

Clustering

Clustering Effect of (Linearized) Adversarial Robust Models

1 code implementation25 Nov 2021 Yang Bai, Xin Yan, Yong Jiang, Shu-Tao Xia, Yisen Wang

Adversarial robustness has received increasing attention along with the study of adversarial examples.

Adversarial Robustness Clustering +1

AdaCompress: Adaptive Compression for Online Computer Vision Services

1 code implementation17 Sep 2019 Hongshan Li, Yu Guo, Zhi Wang, Shu-Tao Xia, Wenwu Zhu

Then we train the agent in a reinforcement learning way to adapt it for different deep learning cloud services that act as the {\em interactive training environment} and feeding a reward with comprehensive consideration of accuracy and data size.

Multimedia Image and Video Processing

Visual Privacy Protection via Mapping Distortion

1 code implementation5 Nov 2019 Yiming Li, Peidong Liu, Yong Jiang, Shu-Tao Xia

To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since this relation provides a great amount of information and can be used in other scenarios.

An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning

1 code implementation23 Feb 2020 Xue Yang, Yan Feng, Weijun Fang, Jun Shao, Xiaohu Tang, Shu-Tao Xia, Rongxing Lu

However, the strong defence ability and high learning accuracy of these schemes cannot be ensured at the same time, which will impede the wide application of FL in practice (especially for medical or financial institutions that require both high accuracy and strong privacy guarantee).

Federated Learning

Versatile Weight Attack via Flipping Limited Bits

1 code implementation25 Jul 2022 Jiawang Bai, Baoyuan Wu, Zhifeng Li, Shu-Tao Xia

Utilizing the latest technique in integer programming, we equivalently reformulate this MIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method.

Backdoor Attack

Learnable Hypergraph Laplacian for Hypergraph Learning

1 code implementation10 Jun 2021 Jiying Zhang, Yuzhao Chen, Xi Xiao, Runiu Lu, Shu-Tao Xia

HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data.

Graph Classification Node Classification

Learnable Hypergraph Laplacian for Hypergraph Learning

1 code implementation12 Jun 2021 Jiying Zhang, Yuzhao Chen, Xi Xiao, Runiu Lu, Shu-Tao Xia

Hypergraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph-structured data.

Graph Classification Node Classification

Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment

1 code implementation25 Nov 2021 Bowen Zhao, Chen Chen, Qian-Wei Wang, Anfeng He, Shu-Tao Xia

For challenge B, we point out that the gradient contribution statistics can be a reliable indicator to inspect whether the optimization is dominated by bias-aligned samples.

Fairness

MOVE: Effective and Harmless Ownership Verification via Embedded External Features

1 code implementation4 Aug 2022 Yiming Li, Linghui Zhu, Xiaojun Jia, Yang Bai, Yong Jiang, Shu-Tao Xia, Xiaochun Cao

In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features.

Style Transfer

Backdoor Defense via Suppressing Model Shortcuts

1 code implementation2 Nov 2022 Sheng Yang, Yiming Li, Yong Jiang, Shu-Tao Xia

Recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks during the training process.

backdoor defense

Backdoor Attack with Sparse and Invisible Trigger

1 code implementation11 May 2023 Yinghua Gao, Yiming Li, Xueluan Gong, Zhifeng Li, Shu-Tao Xia, Qian Wang

More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack.

Backdoor Attack

Unifying Decision Trees Split Criteria Using Tsallis Entropy

no code implementations25 Nov 2015 Yisen Wang, Chaobing Song, Shu-Tao Xia

In this paper, a Tsallis Entropy Criterion (TEC) algorithm is proposed to unify Shannon entropy, Gain Ratio and Gini index, which generalizes the split criteria of decision trees.

Nonextensive information theoretical machine

no code implementations21 Apr 2016 Chaobing Song, Shu-Tao Xia

In this paper, we propose a new discriminative model named \emph{nonextensive information theoretical machine (NITM)} based on nonextensive generalization of Shannon information theory.

Bayesian linear regression with Student-t assumptions

no code implementations15 Apr 2016 Chaobing Song, Shu-Tao Xia

In this paper, we propose a Bayesian linear regression model with Student-t assumptions (BLRS), which can be inferred exactly.

regression

Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization

no code implementations WS 2018 Jilei Wang, Shiying Luo, Weiyan Shi, Tao Dai, Shu-Tao Xia

Learning vector space representation of words (i. e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario.

Cross-Lingual Word Embeddings Machine Translation +4

Multinomial Random Forest: Toward Consistency and Privacy-Preservation

no code implementations10 Mar 2019 Yiming Li, Jiawang Bai, Jiawei Li, Xue Yang, Yong Jiang, Chun Li, Shu-Tao Xia

Despite the impressive performance of random forests (RF), its theoretical properties have not been thoroughly understood.

General Classification

Rectified Decision Trees: Towards Interpretability, Compression and Empirical Soundness

no code implementations14 Mar 2019 Jiawang Bai, Yiming Li, Jiawei Li, Yong Jiang, Shu-Tao Xia

How to obtain a model with good interpretability and performance has always been an important research topic.

Knowledge Distillation

Adaptive Regularization of Labels

no code implementations15 Aug 2019 Qianggang Ding, Sifan Wu, Hao Sun, Jiadong Guo, Shu-Tao Xia

In addition, label regularization techniques such as label smoothing and label disturbance have also been proposed with the motivation of adding a stochastic perturbation to labels.

Data Augmentation Knowledge Distillation +2

Adversarial Defense via Local Flatness Regularization

no code implementations27 Oct 2019 Jia Xu, Yiming Li, Yong Jiang, Shu-Tao Xia

In this paper, we define the local flatness of the loss surface as the maximum value of the chosen norm of the gradient regarding to the input within a neighborhood centered on the benign sample, and discuss the relationship between the local flatness and adversarial vulnerability.

Adversarial Defense

Deep Flow Collaborative Network for Online Visual Tracking

no code implementations5 Nov 2019 Peidong Liu, Xiyu Yan, Yong Jiang, Shu-Tao Xia

The deep learning-based visual tracking algorithms such as MDNet achieve high performance leveraging to the feature extraction ability of a deep neural network.

Optical Flow Estimation Scheduling +1

Automatic Financial Feature Construction

no code implementations8 Dec 2019 Jie Fang, Shu-Tao Xia, Jian-Wu Lin, Yong Jiang

According to neural network universal approximation theorem, pre-training can conduct a more effective and explainable evolution process.

Data Augmentation Time Series Analysis

Alpha Discovery Neural Network based on Prior Knowledge

no code implementations26 Dec 2019 Jie Fang, Shu-Tao Xia, Jian-Wu Lin, Zhikang Xia, Xiang Liu, Yong Jiang

This paper proposes Alpha Discovery Neural Network (ADNN), a tailored neural network structure which can automatically construct diversified financial technical indicators based on prior knowledge.

Time Series Time Series Analysis

Adversarial Attack on Deep Product Quantization Network for Image Retrieval

no code implementations26 Feb 2020 Yan Feng, Bin Chen, Tao Dai, Shu-Tao Xia

Deep product quantization network (DPQN) has recently received much attention in fast image retrieval tasks due to its efficiency of encoding high-dimensional visual features especially when dealing with large-scale datasets.

Adversarial Attack Image Retrieval +2

Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels

no code implementations26 Mar 2020 Xianbin Lv, Dongxian Wu, Shu-Tao Xia

Probabilistic modeling, which consists of a classifier and a transition matrix, depicts the transformation from true labels to noisy labels and is a promising approach.

Rethinking the Trigger of Backdoor Attack

no code implementations9 Apr 2020 Yiming Li, Tongqing Zhai, Baoyuan Wu, Yong Jiang, Zhifeng Li, Shu-Tao Xia

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it performs well on benign samples.

Backdoor Attack backdoor defense

Temporal Calibrated Regularization for Robust Noisy Label Learning

no code implementations1 Jul 2020 Dongxian Wu, Yisen Wang, Zhuobin Zheng, Shu-Tao Xia

Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets.

Neural Network-based Automatic Factor Construction

no code implementations14 Aug 2020 Jie Fang, Jian-Wu Lin, Shu-Tao Xia, Yong Jiang, Zhikang Xia, Xiang Liu

This paper proposes Neural Network-based Automatic Factor Construction (NNAFC), a tailored neural network framework that can automatically construct diversified financial factors based on financial domain knowledge and a variety of neural network structures.

Time Series Time Series Analysis

Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning

no code implementations21 Aug 2020 Yiming Li, Jiawang Bai, Jiawei Li, Xue Yang, Yong Jiang, Shu-Tao Xia

Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality.

BIG-bench Machine Learning Knowledge Distillation

JSRT: James-Stein Regression Tree

no code implementations18 Oct 2020 Xingchun Xiang, Qingtao Tang, Huaixuan Zhang, Tao Dai, Jiawei Li, Shu-Tao Xia

To address this issue, we propose a novel regression tree, named James-Stein Regression Tree (JSRT) by considering global information from different nodes.

regression

DPAttack: Diffused Patch Attacks against Universal Object Detection

no code implementations16 Oct 2020 Shudeng Wu, Tao Dai, Shu-Tao Xia

Recently, deep neural networks (DNNs) have been widely and successfully used in Object Detection, e. g.

Object object-detection +1

Hidden Backdoor Attack against Semantic Segmentation Models

no code implementations6 Mar 2021 Yiming Li, YanJie Li, Yalei Lv, Yong Jiang, Shu-Tao Xia

Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data.

Autonomous Driving Backdoor Attack +2

Backdoor Attack in the Physical World

no code implementations6 Apr 2021 Yiming Li, Tongqing Zhai, Yong Jiang, Zhifeng Li, Shu-Tao Xia

We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training.

Backdoor Attack

Deep Dirichlet Process Mixture Models

no code implementations29 Sep 2021 Naiqi Li, Wenjie Li, Yong Jiang, Shu-Tao Xia

In this paper we propose the deep Dirichlet process mixture (DDPM) model, which is an unsupervised method that simultaneously performs clustering and feature learning.

Clustering

Does Adversarial Robustness Really Imply Backdoor Vulnerability?

no code implementations29 Sep 2021 Yinghua Gao, Dongxian Wu, Jingfeng Zhang, Shu-Tao Xia, Gang Niu, Masashi Sugiyama

Based on thorough experiments, we find that such trade-off ignores the interactions between the perturbation budget of adversarial training and the magnitude of the backdoor trigger.

Adversarial Robustness

Training Interpretable Convolutional Neural Networks towards Class-specific Filters

no code implementations25 Sep 2019 Haoyu Liang, Zhihao Ouyang, Hang Su, Yuyuan Zeng, Zihao He, Shu-Tao Xia, Jun Zhu, Bo Zhang

Convolutional neural networks (CNNs) have often been treated as “black-box” and successfully used in a range of tasks.

Universal Adversarial Head: Practical Protection against Video Data Leakage

no code implementations ICML Workshop AML 2021 Jiawang Bai, Bin Chen, Dongxian Wu, Chaoning Zhang, Shu-Tao Xia

We propose $universal \ adversarial \ head$ (UAH), which crafts adversarial query videos by prepending the original videos with a sequence of adversarial frames to perturb the normal hash codes in the Hamming space.

Deep Hashing Video Retrieval

On the Effectiveness of Adversarial Training against Backdoor Attacks

no code implementations22 Feb 2022 Yinghua Gao, Dongxian Wu, Jingfeng Zhang, Guanhao Gan, Shu-Tao Xia, Gang Niu, Masashi Sugiyama

To explore whether adversarial training could defend against backdoor attacks or not, we conduct extensive experiments across different threat models and perturbation budgets, and find the threat model in adversarial training matters.

A Comparative Study of Feature Expansion Unit for 3D Point Cloud Upsampling

no code implementations19 May 2022 Qiang Li, Tao Dai, Shu-Tao Xia

Recently, deep learning methods have shown great success in 3D point cloud upsampling.

Image Super-Resolution

VFed-SSD: Towards Practical Vertical Federated Advertising

no code implementations31 May 2022 Wenjie Li, Qiaolin Xia, Junfeng Deng, Hao Cheng, Jiangming Liu, Kouying Xue, Yong Cheng, Shu-Tao Xia

As an emerging secure learning paradigm in lever-aging cross-agency private data, vertical federatedlearning (VFL) is expected to improve advertising models by enabling the joint learning of complementary user attributes privately owned by the advertiser and the publisher.

Federated Learning Knowledge Distillation +1

Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain

no code implementations6 Sep 2022 Yujun Huang, Bin Chen, Shiyu Qin, Jiawei Li, YaoWei Wang, Tao Dai, Shu-Tao Xia

Specifically, MSFDPM consists of a side information feature extractor, a multi-scale feature domain patch matching module, and a multi-scale feature fusion network.

Image Compression Patch Matching

Vertical Semi-Federated Learning for Efficient Online Advertising

no code implementations30 Sep 2022 Wenjie Li, Qiaolin Xia, Hao Cheng, Kouyin Xue, Shu-Tao Xia

Specifically, we build an inference-efficient single-party student model applicable to the whole sample space and meanwhile maintain the advantage of the federated feature extension.

Vertical Federated Learning

Controller-Guided Partial Label Consistency Regularization with Unlabeled Data

no code implementations20 Oct 2022 Qian-Wei Wang, Bowen Zhao, Mingyan Zhu, Tianxiang Li, Zimo Liu, Shu-Tao Xia

Partial label learning (PLL) learns from training examples each associated with multiple candidate labels, among which only one is valid.

Contrastive Learning Data Augmentation +2

BATT: Backdoor Attack with Transformation-based Triggers

no code implementations2 Nov 2022 Tong Xu, Yiming Li, Yong Jiang, Shu-Tao Xia

The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger patterns during the training process.

Backdoor Attack

DELTA: degradation-free fully test-time adaptation

no code implementations30 Jan 2023 Bowen Zhao, Chen Chen, Shu-Tao Xia

However, we find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning.

Self-Learning Test-time Adaptation

Delving into Identify-Emphasize Paradigm for Combating Unknown Bias

no code implementations22 Feb 2023 Bowen Zhao, Chen Chen, Qian-Wei Wang, Anfeng He, Shu-Tao Xia

For challenge B, we point out that the gradient contribution statistics can be a reliable indicator to inspect whether the optimization is dominated by bias-aligned samples.

Unsupervised Anomaly Detection with Local-Sensitive VQVAE and Global-Sensitive Transformers

no code implementations29 Mar 2023 Mingqing Wang, Jiawei Li, Zhenyang Li, Chengxiao Luo, Bin Chen, Shu-Tao Xia, Zhi Wang

In this work, the VQVAE focus on feature extraction and reconstruction of images, and the transformers fit the manifold and locate anomalies in the latent space.

Unsupervised Anomaly Detection

Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding

no code implementations18 May 2023 Taolin Zhang, Sunan He, Dai Tao, Bin Chen, Zhi Wang, Shu-Tao Xia

In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks.

Contrastive Learning Object +2

Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model

no code implementations ICCV 2023 Xinyi Zhang, Naiqi Li, Jiawei Li, Tao Dai, Yong Jiang, Shu-Tao Xia

Unsupervised surface anomaly detection aims at discovering and localizing anomalous patterns using only anomaly-free training samples.

Unsupervised Anomaly Detection

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP

no code implementations26 Nov 2023 Jiawang Bai, Kuofeng Gao, Shaobo Min, Shu-Tao Xia, Zhifeng Li, Wei Liu

Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks.

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger

no code implementations3 Dec 2023 Yiming Li, Mingyan Zhu, Junfeng Guo, Tao Wei, Shu-Tao Xia, Zhan Qin

We argue that the intensity constraint of existing SSBAs is mostly because their trigger patterns are `content-irrelevant' and therefore act as `noises' for both humans and DNNs.

Attribute Backdoor Attack

Fast Implicit Neural Representation Image Codec in Resource-limited Devices

no code implementations23 Jan 2024 Xiang Liu, Jiahong Chen, Bin Chen, Zimo Liu, Baoyi An, Shu-Tao Xia

With different parameter settings, our method can outperform popular AE-based codecs in constrained environments in terms of both quality and decoding time, or achieve state-of-the-art reconstruction quality compared to other INR codecs.

Computational Efficiency Image Compression

MB-RACS: Measurement-Bounds-based Rate-Adaptive Image Compressed Sensing Network

no code implementations19 Jan 2024 Yujun Huang, Bin Chen, Naiqi Li, Baoyi An, Shu-Tao Xia, YaoWei Wang

In this paper, we propose a Measurement-Bounds-based Rate-Adaptive Image Compressed Sensing Network (MB-RACS) framework, which aims to adaptively determine the sampling rate for each image block in accordance with traditional measurement bounds theory.

Image Compressed Sensing

FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs

no code implementations20 Mar 2024 Jinmin Li, Kuofeng Gao, Yang Bai, Jingyun Zhang, Shu-Tao Xia, Yisen Wang

Despite the remarkable performance of video-based large language models (LLMs), their adversarial threat remains unexplored.

Adversarial Attack

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