0

Inherently Faithful Attention Maps for Vision Transformers

An attention-based method using learned binary masks improves robustness in object perception by focusing on relevant image regions while filtering out spurious information.

Year
2025
Venue
arXiv 2025
Authors
4
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2506.08915ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

We introduce an attention-based method that uses learned binary attention masks to ensure that only attended image regions influence the prediction. Context can strongly affect object perception, sometimes leading to biased representations, particularly when objects appear in out-of-distribution backgrounds. At the same time, many image-level object-centric tasks require identifying relevant regions, often requiring context. To address this conundrum, we propose a two-stage framework: stage 1 processes the full image to discover object parts and identify task-relevant regions, while stage 2 leverages input attention masking to restrict its receptive field to these regions, enabling a focused analysis while filtering out potentially spurious information. Both stages are trained jointly, allowing stage 2 to refine stage 1. Extensive experiments across diverse benchmarks demonstrate that our approach significantly improves robustness against spurious correlations and out-of-distribution backgrounds.

Authors

4