# wofmanaf/rest

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/wofmanaf-rest).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

291 stars · 30 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/wofmanaf/ResT
- awesome-repositories: https://awesome-repositories.com/repository/wofmanaf-rest.md

## Description

(2022/05/10) Code of ResTV2 is released! ResTv2 simplifies the EMSA structure in ResTv1 (i.e., eliminating the multi-head interaction part) and employs an upsample operation to reconstruct the lost medium- and high-frequency information caused by the downsampling operation.

## Tags

### Part of an Awesome List

- [Attention Mechanisms](https://awesome-repositories.com/f/awesome-lists/ai/attention-mechanisms.md) — Efficient transformer architectures for visual recognition.
- [Efficient Vision Architectures](https://awesome-repositories.com/f/awesome-lists/ai/efficient-vision-architectures.md) — Provides an efficient transformer backbone for visual recognition tasks.
- [Efficient Vision Transformers](https://awesome-repositories.com/f/awesome-lists/ai/efficient-vision-transformers.md) — Provides an efficient transformer backbone for visual recognition tasks.
- [Vision Transformers](https://awesome-repositories.com/f/awesome-lists/ai/vision-transformers.md) — Efficient transformer design optimized for visual recognition.