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

被引:19
|
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
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] Improving vision transformer for medical image classification via token-wise perturbation
    Li, Yuexiang
    Huang, Yawen
    He, Nanjun
    Ma, Kai
    Zheng, Yefeng
    Journal of Visual Communication and Image Representation, 2024, 98
  • [22] Histopathological Image Classification based on Self-Supervised Vision Transformer and Weak Labels
    Gul, Ahmet Gokberk
    Cetin, Oezdemir
    Reich, Christoph
    Flinner, Nadine
    Prangemeier, Tim
    Koeppl, Heinz
    MEDICAL IMAGING 2022: DIGITAL AND COMPUTATIONAL PATHOLOGY, 2022, 12039
  • [23] MAT-VIT:A Vision Transformer with MAE-Based Self-Supervised Auxiliary Task for Medical Image Classification
    Han, Yufei
    Chen, Haoyuan
    Yao, Linwei
    Li, Kuan
    Yin, Jianping
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 2040 - 2046
  • [24] Vision Transformer With Contrastive Learning for Hyperspectral Image Classification
    Zhou, Heng
    Zhang, Xin
    Zhang, Chunlei
    Ma, Qiaoyu
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
  • [25] CSiT: A Multiscale Vision Transformer for Hyperspectral Image Classification
    He, Wenxuan
    Huang, Weiliang
    Liao, Shuhong
    Xu, Zhen
    Yan, Jingwen
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 9266 - 9277
  • [26] Hyperspectral image classification with embedded linear vision transformer
    Tan, Yunfei
    Li, Ming
    Yuan, Longfa
    Shi, Chaoshan
    Luo, Yonghang
    Wen, Guihao
    EARTH SCIENCE INFORMATICS, 2025, 18 (01)
  • [27] Image Classification Using Vision Transformer for EtC Images
    Hamano, Genki
    Imaizumi, Shoko
    Kiya, Hitoshi
    PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, : 1506 - 1513
  • [28] Compressed-Domain Vision Transformer for Image Classification
    Ji, Ruolei
    Karam, Lina J.
    IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS, 2024, 14 (02) : 299 - 310
  • [29] Vision Transformer (ViT)-based Applications in Image Classification
    Huo, Yingzi
    Jin, Kai
    Cai, Jiahong
    Xiong, Huixuan
    Pang, Jiacheng
    2023 IEEE 9TH INTL CONFERENCE ON BIG DATA SECURITY ON CLOUD, BIGDATASECURITY, IEEE INTL CONFERENCE ON HIGH PERFORMANCE AND SMART COMPUTING, HPSC AND IEEE INTL CONFERENCE ON INTELLIGENT DATA AND SECURITY, IDS, 2023, : 135 - 140
  • [30] CSiT: A Multiscale Vision Transformer for Hyperspectral Image Classification
    He, Wenxuan
    Huang, Weiliang
    Liao, Shuhong
    Xu, Zhen
    Yan, Jingwen
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15 : 9266 - 9277