# Robustifying Token Attention for Vision Transformers

arXiv: https://arxiv.org/abs/2303.11126 · HTML: https://mlsanity.com/paper/2303.11126/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 74 references that are in the map.
- First posted on arXiv 20 Mar 2023.

## Builds on (most cited first, 30 of 65)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)

## Built on by (most cited first, 19 of 19)

- [One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation](https://mlsanity.com/paper/2502.01993/) (2025)
- [Adaptive Sharpness-Aware Pruning for Robust Sparse Networks](https://mlsanity.com/paper/2306.14306/) (2023)
- [RoDLA: Benchmarking the Robustness of Document Layout Analysis Models](https://mlsanity.com/paper/2403.14442/) (2024)
- [Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions](https://mlsanity.com/paper/2403.20254/) (2024)
- [ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.21233/) (2025)
- [Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modeling](https://mlsanity.com/paper/2406.11891/) (2024)
- [Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness](https://mlsanity.com/paper/2407.08972/) (2024)
- [Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?](https://mlsanity.com/paper/2505.04835/) (2025)
- [AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer](https://mlsanity.com/paper/2406.08298/) (2024)
- [LOTFormer: Doubly-Stochastic Linear Attention via Low-Rank Optimal Transport](https://mlsanity.com/paper/2509.23436/) (2025)
- [Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals](https://mlsanity.com/paper/2503.06473/) (2025)
- [Robustifying Point Cloud Networks by Refocusing](https://mlsanity.com/paper/2308.05525/) (2023)
- [A Manifold Representation of the Key in Vision Transformers](https://mlsanity.com/paper/2402.00534/) (2024)
- [SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers](https://mlsanity.com/paper/2409.19850/) (2024)
- [Enhancing Self-Supervised Visual Representation Learning via Low-Rank Adapted LLMs](https://mlsanity.com/paper/2507.00754/) (2025)
- [VisMoDAl: Visual Analytics for Evaluating and Improving Corruption Robustness of Vision-Language Models](https://mlsanity.com/paper/2509.14571/) (2025)
- [Spike-NVPT: Learning Robust Visual Prompts via Bio-Inspired Temporal Filtering and Discretization](https://mlsanity.com/paper/2604.18284/) (2026)
- [REDI: Corpus Aware Patch Ranking for DINOv3 Token Reduction](https://mlsanity.com/paper/2606.31676/) (2026)
- [What Does Attention Transfer Transfer? Attention Structure and Robustness in Vision Transformers](https://mlsanity.com/paper/2608.18399/) (2026)

## Abstract (arXiv)

Despite the success of vision transformers (ViTs), they still suffer from significant drops in accuracy in the presence of common corruptions, such as noise or blur. Interestingly, we observe that the attention mechanism of ViTs tends to rely on few important tokens, a phenomenon we call token overfocusing. More critically, these tokens are not robust to corruptions, often leading to highly diverging attention patterns. In this paper, we intend to alleviate this overfocusing issue and make attention more stable through two general techniques: First, our Token-aware Average Pooling (TAP) module encourages the local neighborhood of each token to take part in the attention mechanism. Specifically, TAP learns average pooling schemes for each token such that the information of potentially important tokens in the neighborhood can adaptively be taken into account. Second, we force the output tokens to aggregate information from a diverse set of input tokens rather than focusing on just a few by using our Attention Diversification Loss (ADL). We achieve this by penalizing high cosine similarity between the attention vectors of different tokens. In experiments, we apply our methods to a wide range of transformer architectures and improve robustness significantly. For example, we improve corruption robustness on ImageNet-C by 2.4% while improving accuracy by 0.4% based on state-of-the-art robust architecture FAN. Also, when fine-tuning on semantic segmentation tasks, we improve robustness on CityScapes-C by 2.4% and ACDC by 3.0%. Our code is available at https://github.com/guoyongcs/TAPADL.