# What Helps---and What Hurts: Bidirectional Explanations for Vision Transformers

arXiv: https://arxiv.org/abs/2603.01605 · HTML: https://mlsanity.com/paper/2603.01605/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [ML-LOO: Detecting Adversarial Examples with Feature Attribution](https://mlsanity.com/paper/1906.03499/) (2019)
- [Learning to Estimate Shapley Values with Vision Transformers](https://mlsanity.com/paper/2206.05282/) (2022)
- [Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples](https://mlsanity.com/paper/1810.11580/) (2018)
- [Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention](https://mlsanity.com/paper/2402.04563/) (2024)
- [Class-Discriminative Attention Maps for Vision Transformers](https://mlsanity.com/paper/2312.02364/) (2023)

## Abstract (arXiv)

Vision Transformers (ViTs) achieve strong performance in visual recognition, yet their decision-making remains difficult to interpret. We propose BiCAM, a bidirectional class activation mapping method that captures both supportive (positive) and suppressive (negative) contributions to model predictions. Unlike prior CAM-based approaches that discard negative signals, BiCAM preserves signed attributions to produce more complete and contrastive explanations. BiCAM further introduces a Positive-to-Negative Ratio (PNR) that summarizes attribution balance and enables lightweight detection of adversarial examples without retraining. Across ImageNet, VOC, and COCO, BiCAM improves localization and faithfulness while remaining computationally efficient. It generalizes to multiple ViT variants, including DeiT and Swin. These results suggest the importance of modeling both supportive and suppressive evidence for interpreting transformer-based vision models.