Inherently Faithful Attention Maps for Vision Transformers
Abstract
An attention-based method using learned binary masks improves robustness in object perception by focusing on relevant image regions while filtering out spurious information.
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.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models (2025)
- Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization (2025)
- GMAR: Gradient-Driven Multi-Head Attention Rollout for Vision Transformer Interpretability (2025)
- Vision-Centric Representation-Efficient Fine-Tuning for Robust Universal Foreground Segmentation (2025)
- Object-level Self-Distillation for Vision Pretraining (2025)
- The Missing Point in Vision Transformers for Universal Image Segmentation (2025)
- From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper