掩码注意力作为提升视觉Transformer可解释性的机制
Masked Attention as a Mechanism for Improving Interpretability of Vision Transformers
AI总结：
提出在视觉Transformer注意力机制中显式掩码背景的方法，通过排除背景token提升模型鲁棒性与可解释性，在前列腺癌分级案例中表现与自注意力相当且提供更准确的注意力热图。
摘要：
视觉Transformer是当前组织病理学基础模型研究热潮的核心。它们通过将图像按照规则网格分割成较小的图像块来处理图像，而不考虑图像内容。然而，并非图像的所有部分对其理解都同等重要。在计算病理学中尤其如此，因为背景完全不提供信息，并且可能引入会误导预测的伪影。为了解决这个问题，我们提出了一种新方法，在视觉Transformer的注意力机制中显式地掩码背景。这确保了对应于背景图像块的token不会对最终的图像表示产生贡献，从而提高了模型的鲁棒性和可解释性。我们使用全切片图像中的前列腺癌分级作为案例研究来验证我们的方法。我们的结果表明，该方法实现了与普通自注意力相当的性能，同时提供了更准确且具有临床意义的注意力热图。
英文摘要：
Vision Transformers are at the heart of the current surge of interest in foundation models for histopathology. They process images by breaking them into smaller patches following a regular grid, regardless of their content. Yet, not all parts of an image are equally relevant for its understanding. This is particularly true in computational pathology where background is completely non-informative and may introduce artefacts that could mislead predictions. To address this issue, we propose a novel method that explicitly masks background in Vision Transformers' attention mechanism. This ensures tokens corresponding to background patches do not contribute to the final image representation, thereby improving model robustness and interpretability. We validate our approach using prostate cancer grading from whole-slide images as a case study. Our results demonstrate that it achieves comparable performance with plain self-attention while providing more accurate and clinically meaningful attention heatmaps.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
