Amshaker / SwiftFormer
[ICCV'23] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
☆274Updated last year
Alternatives and similar repositories for SwiftFormer:
Users that are interested in SwiftFormer are comparing it to the libraries listed below
- InceptionNeXt: When Inception Meets ConvNeXt (CVPR 2024)☆283Updated 3 months ago
- MetaFormer Baselines for Vision (TPAMI 2024)☆454Updated 9 months ago
- [ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer☆317Updated last month
- [ICCV 2023] Official PyTorch implementation of "Rethinking Mobile Block for Efficient Attention-based Models"☆238Updated last year
- [CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Ap…☆363Updated last year
- Official Code of Paper "Reversible Column Networks" "RevColv2"☆259Updated last year
- Code and models for mobile-former☆123Updated 2 years ago
- [NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"☆270Updated last year
- Code Implementation of EfficientVMamba☆202Updated 11 months ago
- Official repository of Slide-Transformer (CVPR2023)☆167Updated 6 months ago
- Lite Vision Transformer (CVPR 2022)