# Optimizing Relevance Maps of Vision Transformers Improves Robustness

arXiv: https://arxiv.org/abs/2206.01161 · HTML: https://mlsanity.com/paper/2206.01161/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 83 references that are in the map.
- First posted on arXiv 2 Jun 2022.

## Builds on (most cited first, 30 of 55)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [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)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)

## Built on by (most cited first, 30 of 41)

- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models](https://mlsanity.com/paper/2207.11514/) (2022)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words](https://mlsanity.com/paper/2309.16108/) (2023)
- [ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification](https://mlsanity.com/paper/2304.05538/) (2023)
- [Backward Lens: Projecting Language Model Gradients into the Vocabulary Space](https://mlsanity.com/paper/2402.12865/) (2024)
- [Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting](https://mlsanity.com/paper/2404.17245/) (2024)
- [Studying How to Efficiently and Effectively Guide Models with Explanations](https://mlsanity.com/paper/2303.11932/) (2023)
- [Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation](https://mlsanity.com/paper/2405.16504/) (2024)
- [Contextual Vision Transformers for Robust Representation Learning](https://mlsanity.com/paper/2305.19402/) (2023)
- [The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers](https://mlsanity.com/paper/2302.10494/) (2023)
- [Attention-aware Semantic Communications for Collaborative Inference](https://mlsanity.com/paper/2404.07217/) (2024)
- [Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers](https://mlsanity.com/paper/2405.03730/) (2024)
- [ACTRESS: Active Retraining for Semi-supervised Visual Grounding](https://mlsanity.com/paper/2407.03251/) (2024)
- [FOCUS: Fused Observation of Channels for Unveiling Spectra](https://mlsanity.com/paper/2507.14787/) (2025)
- [Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training](https://mlsanity.com/paper/2406.00685/) (2024)
- [GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets](https://mlsanity.com/paper/2408.14131/) (2024)
- [Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers](https://mlsanity.com/paper/2507.04388/) (2025)
- [LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions](https://mlsanity.com/paper/2411.16760/) (2024)
- [Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts](https://mlsanity.com/paper/2303.17595/) (2023)
- [SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition](https://mlsanity.com/paper/2503.15986/) (2025)
- [A Meaningful Perturbation Metric for Evaluating Explainability Methods](https://mlsanity.com/paper/2504.06800/) (2025)
- [X-Edit: Detecting and Localizing Edits in Images Altered by Text-Guided Diffusion Models](https://mlsanity.com/paper/2505.11753/) (2025)
- [PV2TEA: Patching Visual Modality to Textual-Established Information Extraction](https://mlsanity.com/paper/2306.01016/) (2023)
- [MaskInversion: Localized Embeddings via Optimization of Explainability Maps](https://mlsanity.com/paper/2407.20034/) (2024)
- [SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers](https://mlsanity.com/paper/2409.19850/) (2024)
- [FastRM: An efficient and automatic explainability framework for multimodal generative models](https://mlsanity.com/paper/2412.01487/) (2024)
- [Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?](https://mlsanity.com/paper/2503.10632/) (2025)
- [C-LEAD: Contrastive Learning for Enhanced Adversarial Defense](https://mlsanity.com/paper/2510.27249/) (2025)

## Abstract (arXiv)

It has been observed that visual classification models often rely mostly on the image background, neglecting the foreground, which hurts their robustness to distribution changes. To alleviate this shortcoming, we propose to monitor the model's relevancy signal and manipulate it such that the model is focused on the foreground object. This is done as a finetuning step, involving relatively few samples consisting of pairs of images and their associated foreground masks. Specifically, we encourage the model's relevancy map (i) to assign lower relevance to background regions, (ii) to consider as much information as possible from the foreground, and (iii) we encourage the decisions to have high confidence. When applied to Vision Transformer (ViT) models, a marked improvement in robustness to domain shifts is observed. Moreover, the foreground masks can be obtained automatically, from a self-supervised variant of the ViT model itself; therefore no additional supervision is required.