Vision Transformers (ViTs) and Swin Transformers (Swin) are currently
state-of-the-art in computational pathology. However, domain experts are still
reluctant to use these models due to their lack of interpretability. This is
not surprising, as critical decisions need to be transparent and
understandable. The most common approach to understanding transformers is to
visualize their attention. However, attention maps of ViTs are often
fragmented, leading to unsatisfactory explanations. Here, we introduce a novel
architecture called the B-cos Vision Transformer (BvT) that is designed to be
more interpretable. It replaces all linear transformations with the B-cos
transform to promote weight-input alignment. In a blinded study, medical
experts clearly ranked BvTs above ViTs, suggesting that our network is better
at capturing biomedically relevant structures. This is also true for the B-cos
Swin Transformer (Bwin). Compared to the Swin Transformer, it even improves the
F1-score by up to 4.7% on two public datasets.

通过引入一种新的架构，即 B-cos Vision Transformer，以提高可解释性，本文证明了 B-cos Swin Transformer 在医学相关任务中超越了 Vision Transformers，并在两个公共数据集上提高了 F1 分数高达 4.7%。