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
  • [1] Weakly-Supervised Self-Ensembling Vision Transformer for MRI Cardiac Segmentation
    Wang, Ziyang
    Mang, Haodong
    Liu, Yang
    2023 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI, 2023, : 101 - 102
  • [2] MedViT: A robust vision transformer for generalized medical image classification
    Manzari, Omid Nejati
    Ahmadabadi, Hamid
    Kashiani, Hossein
    Shokouhi, Shahriar B.
    Ayatollahi, Ahmad
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 157
  • [3] SEDA: Self-ensembling ViT with Defensive Distillation and Adversarial Training for Robust Chest X-Rays Classification
    Imam, Raza
    Almakky, Ibrahim
    Alrashdi, Salma
    Alrashdi, Baketah
    Yaqub, Mohammad
    DOMAIN ADAPTATION AND REPRESENTATION TRANSFER, DART 2023, 2024, 14293 : 126 - 135
  • [4] Quantitative regularization in robust vision transformer for remote sensing image classification
    Song, Huaxiang
    Yuan, Yuxuan
    Ouyang, Zhiwei
    Yang, Yu
    Xiang, Hui
    PHOTOGRAMMETRIC RECORD, 2024, 39 (186) : 340 - 372
  • [5] The Application of Vision Transformer in Image Classification
    He, Zhixuan
    2022 THE 6TH INTERNATIONAL CONFERENCE ON VIRTUAL AND AUGMENTED REALITY SIMULATIONS, ICVARS 2022, 2022, : 56 - 63
  • [6] RViT: Robust Fusion Vision Transformer with Variational Hierarchical Denoising Process for Image Classification
    Lin, Zhenghong
    Wu, Yuze
    Chen, Jiawei
    Wang, Shiping
    GUIDANCE NAVIGATION AND CONTROL, 2024, 04 (03)
  • [7] 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
  • [8] 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
  • [9] 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
  • [10] MetaV: A Pioneer in feature Augmented Meta-Learning Based Vision Transformer for Medical Image Classification
    Ansari, Shaharyar Alam
    Agrawal, Arun Prakash
    Wajid, Mohd Anas
    Wajid, Mohammad Saif
    Zafar, Aasim
    INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES, 2024, 16 (02) : 469 - 488