# Patch Pruning Strategy Based on Robust Statistical Measures of Attention Weight Diversity in Vision Transformers

arXiv: https://arxiv.org/abs/2507.19175 · HTML: https://mlsanity.com/paper/2507.19175/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [DeepViT: Towards Deeper Vision Transformer](https://mlsanity.com/paper/2103.11886/) (2021)
- [Multi-Head Attention with Disagreement Regularization](https://mlsanity.com/paper/1810.10183/) (2018)
- [Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations](https://mlsanity.com/paper/1910.00058/) (2019)

## Built on by (most cited first, 1 of 1)

- [R'enyi Attention Entropy for Patch Pruning](https://mlsanity.com/paper/2604.03803/) (2026)

## Abstract (arXiv)

Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significantly to their high performance. However, it is known to incur a quadratic computational complexity with respect to the number of patches. One promising approach to address this issue is patch pruning, which improves computational efficiency by identifying and removing redundant patches. In this work, we propose a patch pruning strategy that evaluates the importance of each patch based on the variance of attention weights across multiple attention heads. This approach is inspired by the design of multi-head self-attention, which aims to capture diverse attention patterns across different subspaces of feature representations. The proposed method can be easily applied during both training and inference, and achieves improved throughput while maintaining classification accuracy in scenarios such as fine-tuning with pre-trained models. In addition, we also found that using robust statistical measures, such as the median absolute deviation in place of variance, to assess patch importance can similarly lead to strong performance. Furthermore, by introducing overlapping patch embeddings, our method achieves better performance with comparable throughput to conventional approaches that utilize all patches.