# Masked Attention as a Mechanism for Improving Interpretability of Vision Transformers

arXiv: https://arxiv.org/abs/2404.18152 · HTML: https://mlsanity.com/paper/2404.18152/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Interpreting biomedical and science models, one of 13 directions in Mechanistic interpretability.
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 28 Apr 2024.

## Placed in

- Mechanistic interpretability / [Interpreting biomedical and science models](https://mlsanity.com/mechinterp/interpreting-biomedical-and-science-models/)

## Builds on (most cited first, 5 of 5)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [Hierarchical Vision Transformers for Context-Aware Prostate Cancer Grading in Whole Slide Images](https://mlsanity.com/paper/2312.12619/) (2023)

## Built on by (most cited first, 1 of 1)

- [Inhibited Self-Attention: Sharpening Focus in Vision Transformers](https://mlsanity.com/paper/2607.12881/) (2026)

## Abstract (arXiv)

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.