|国家预印本平台
首页|Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging

Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging

Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging

来源:Arxiv_logoArxiv
英文摘要

Vision transformers (ViTs) have rapidly gained prominence in medical imaging tasks such as disease classification, segmentation, and detection due to their superior accuracy compared to conventional deep learning models. However, due to their size and complex interactions via the self-attention mechanism, they are not well understood. In particular, it is unclear whether the representations produced by such models are semantically meaningful. In this paper, using a projected gradient-based algorithm, we show that their representations are not semantically meaningful and they are inherently vulnerable to small changes. Images with imperceptible differences can have very different representations; on the other hand, images that should belong to different semantic classes can have nearly identical representations. Such vulnerability can lead to unreliable classification results; for example, unnoticeable changes cause the classification accuracy to be reduced by over 60\%. %. To the best of our knowledge, this is the first work to systematically demonstrate this fundamental lack of semantic meaningfulness in ViT representations for medical image classification, revealing a critical challenge for their deployment in safety-critical systems.

Montasir Shams、Chashi Mahiul Islam、Shaeke Salman、Phat Tran、Xiuwen Liu

医学研究方法

Montasir Shams,Chashi Mahiul Islam,Shaeke Salman,Phat Tran,Xiuwen Liu.Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging[EB/OL].(2025-07-10)[2025-07-16].https://arxiv.org/abs/2507.01788.点此复制

评论