Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image Classification

被引:20
|
作者
Almalik, Faris [1 ]
Yaqub, Mohammad [1 ]
Nandakumar, Karthik [1 ]
机构
[1] Mohamed Bin Zayed Univ, Artificial Intelligence, Abu Dhabi, U Arab Emirates
来源
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT III | 2022年 / 13433卷
关键词
Adversarial attack; Vision transformer; Self-ensemble;
D O I
10.1007/978-3-031-16437-8_36
中图分类号
R445 [影像诊断学];
学科分类号
100207 ;
摘要
Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation. While the vulnerability of CNNs to adversarial attacks is a well-known problem, recent works have shown that ViTs are also susceptible to such attacks and suffer significant performance degradation under attack. The vulnerability of ViTs to carefully engineered adversarial samples raises serious concerns about their safety in clinical settings. In this paper, we propose a novel self-ensembling method to enhance the robustness of ViT in the presence of adversarial attacks. The proposed Self-Ensembling Vision Transformer (SEViT) leverages the fact that feature representations learned by initial blocks of a ViT are relatively unaffected by adversarial perturbations. Learning multiple classifiers based on these intermediate feature representations and combining these predictions with that of the final ViT classifier can provide robustness against adversarial attacks. Measuring the consistency between the various predictions can also help detect adversarial samples. Experiments on two modalities (chest X-ray and fundoscopy) demonstrate the efficacy of SEViT architecture to defend against various adversarial attacks in the gray-box (attacker has full knowledge of the target model, but not the defense mechanism) setting. Code: https://github.com/faresmalik/SEViT
引用
收藏
页码:376 / 386
页数:11
相关论文
共 50 条
  • [21] An enhanced vision transformer with wavelet position embedding for histopathological image classification
    Ding, Meidan
    Qu, Aiping
    Zhong, Haiqin
    Lai, Zhihui
    Xiao, Shuomin
    He, Penghui
    PATTERN RECOGNITION, 2023, 140
  • [22] Vision Transformer With Contrastive Learning for Remote Sensing Image Scene Classification
    Bi, Meiqiao
    Wang, Minghua
    Li, Zhi
    Hong, Danfeng
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 738 - 749
  • [23] SimPoolFormer: A two-stream vision transformer for hyperspectral image classification
    Roy, Swalpa Kumar
    Jamali, Ali
    Chanussot, Jocelyn
    Ghamisi, Pedram
    Ghaderpour, Ebrahim
    Shahabi, Himan
    REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT, 2025, 37
  • [24] A Robust Image Semantic Communication System With Multi-Scale Vision Transformer
    Peng, Xiang
    Qin, Zhijin
    Tao, Xiaoming
    Lu, Jianhua
    Letaief, Khaled B.
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2025, 43 (04) : 1278 - 1291
  • [25] Breast Ultrasound Image BI-RADS Classification Based on Vision Transformer
    Wei, Yanbo
    Ye, Junbo
    Li, Xiaofeng
    Zhao, Yuanyuan
    Wang, Yanwei
    INTERNATIONAL JOURNAL OF MULTIPHYSICS, 2024, 18 (02) : 32 - 39
  • [26] MIL-ViT: A multiple instance vision transformer for fundus image classification
    Bi, Qi
    Sun, Xu
    Yu, Shuang
    Ma, Kai
    Bian, Cheng
    Ning, Munan
    He, Nanjun
    Huang, Yawen
    Li, Yuexiang
    Liu, Hanruo
    Zheng, Yefeng
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 97
  • [27] Lightweight vision image transformer (LViT) model for skin cancer disease classification
    Dwivedi, Tanay
    Chaurasia, Brijesh Kumar
    Shukla, Man Mohan
    INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT, 2024, 15 (10) : 5030 - 5055
  • [28] Network Intrusion Detection Based on Feature Image and Deformable Vision Transformer Classification
    He, Kan
    Zhang, Wei
    Zong, Xuejun
    Lian, Lian
    IEEE ACCESS, 2024, 12 : 44335 - 44350
  • [29] TransMCGC: a recast vision transformer for small-scale image classification tasks
    Jian-Wen Xiang
    Min-Rong Chen
    Pei-Shan Li
    Hao-Li Zou
    Shi-Da Li
    Jun-Jie Huang
    Neural Computing and Applications, 2023, 35 : 7697 - 7718
  • [30] CAEVT: Convolutional Autoencoder Meets Lightweight Vision Transformer for Hyperspectral Image Classification
    Zhang, Zhiwen
    Li, Teng
    Tang, Xuebin
    Hu, Xiang
    Peng, Yuanxi
    SENSORS, 2022, 22 (10)