# Static Key Attention in Vision

arXiv: https://arxiv.org/abs/2412.07049 · HTML: https://mlsanity.com/paper/2412.07049/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Builds on (most cited first, 11 of 11)

- [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)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Pay Attention to MLPs](https://mlsanity.com/paper/2105.08050/) (2021)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Patches Are All You Need?](https://mlsanity.com/paper/2201.09792/) (2022)
- [Inception Transformer](https://mlsanity.com/paper/2205.12956/) (2022)
- [FFNet: MetaMixer-based Efficient Convolutional Mixer Design](https://mlsanity.com/paper/2406.02021/) (2024)

## Abstract (arXiv)

The success of vision transformers is widely attributed to the expressive power of their dynamically parameterized multi-head self-attention mechanism. We examine the impact of substituting the dynamic parameterized key with a static key within the standard attention mechanism in Vision Transformers. Our findings reveal that static key attention mechanisms can match or even exceed the performance of standard self-attention. Integrating static key attention modules into a Metaformer backbone, we find that it serves as a better intermediate stage in hierarchical hybrid architectures, balancing the strengths of depth-wise convolution and self-attention. Experiments on several vision tasks underscore the effectiveness of the static key mechanism, indicating that the typical two-step dynamic parameterization in attention can be streamlined to a single step without impacting performance under certain circumstances.