# Saccade Attention Networks: Using Transfer Learning of Attention to Reduce Network Sizes

arXiv: https://arxiv.org/abs/2604.16485 · HTML: https://mlsanity.com/paper/2604.16485/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 5 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 4 of 4)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Glance and Focus Networks for Dynamic Visual Recognition](https://mlsanity.com/paper/2201.03014/) (2022)
- [Saccader: Improving Accuracy of Hard Attention Models for Vision](https://mlsanity.com/paper/1908.07644/) (2019)

## Abstract (arXiv)

One of the limitations of transformer networks is the sequence length due to the quadratic nature of the attention matrix. Classical self attention uses the entire sequence length, however, the actual attention being used is sparse. Humans use a form of sparse attention when analyzing an image or scene called saccades. Focusing on key features greatly reduces computation time. By using a network (Saccade Attention Network) to learn where to attend from a large pre-trained model, we can use it to pre-process images and greatly reduce network size by reducing the input sequence length to just the key features being attended to. Our results indicate that you can reduce calculations by close to 80% and produce similar results.