# Fair Comparison between Efficient Attentions

arXiv: https://arxiv.org/abs/2206.00244 · HTML: https://mlsanity.com/paper/2206.00244/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 13 of 13)

- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Efficient Attention: Attention with Linear Complexities](https://mlsanity.com/paper/1812.01243/) (2018)
- [XCiT: Cross-Covariance Image Transformers](https://mlsanity.com/paper/2106.09681/) (2021)
- [Fastformer: Additive Attention Can Be All You Need](https://mlsanity.com/paper/2108.09084/) (2021)

## Abstract (arXiv)

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of transformers in various vision tasks that require dense prediction. Many studies aiming at solving this problem have been reported proposed. However, no comparative study of these methods using the same scale has been reported due to different model configurations, training schemes, and new methods. In our paper, we validate these efficient attention models on the ImageNet1K classification task by changing only the attention operation and examining which efficient attention is better.