Atten4Vis / DemystifyLocalViT
Official code for paper "On the Connection between Local Attention and Dynamic Depth-wise Convolution" ICLR 2022 Spotlight
☆183Updated last year
Related projects ⓘ
Alternatives and complementary repositories for DemystifyLocalViT
- [ICLR'22] This is an official implementation for "AS-MLP: An Axial Shifted MLP Architecture for Vision".☆123Updated 2 years ago
- ☆189Updated last year
- Official MegEngine implementation of RepLKNet☆267Updated 2 years ago
- official code for dynamic convolution decomposition☆130Updated 2 years ago
- MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens (CVPR 2022)☆81Updated 2 years ago
- [CVPR2022 - Oral] Official Jax Implementation of Learned Queries for Efficient Local Attention☆114Updated 2 years ago
- CVPR 2022 "Online Convolutional Re-parameterization"☆169Updated 2 years ago
- The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks☆214Updated 2 years ago
- ☆210Updated 2 years ago
- Official implementation for paper "LightViT: Towards Light-Weight Convolution-Free Vision Transformers"☆137Updated 2 years ago
- The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration☆86Updated 2 years ago
- ☆113Updated 2 years ago
- [NeurIPS2022] Official implementation of the paper 'Green Hierarchical Vision Transformer for Masked Image Modeling'.☆170Updated last year
- ☆108Updated 3 years ago
- Lite Vision Transformer (CVPR 2022)☆134Updated 2 years ago
- ☆192Updated 3 years ago
- Accelerating T2t-ViT by 1.6-3.6x.☆247Updated 2 years ago
- Official Code of Paper "Reversible Column Networks" "RevColv2"☆249Updated last year
- MLP-Like Vision Permutator for Visual Recognition (PyTorch)☆190Updated 2 years ago
- The official pytorch implementation of ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias☆103Updated 2 years ago
- The official implementation of ELSA: Enhanced Local Self-Attention for Vision Transformer☆114Updated last year
- Implementation of Convolutional enhanced image Transformer☆100Updated 3 years ago
- HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers (CVPR21 Oral)☆139Updated 3 years ago
- This is an official implementation for "ResT: An Efficient Transformer for Visual Recognition".☆280Updated 2 years ago
- Official implement of "CAT: Cross Attention in Vision Transformer".☆141Updated 2 years ago
- ☆149Updated last year
- This repo contains the code of "ConTNet: Why not use convolution and transformer at the same time?"☆95Updated 3 years ago
- Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.☆149Updated 2 years ago
- DPT: Deformable Patch-based Transformer for Visual Recognition (ACM MM2021)☆148Updated 3 years ago
- A Close Look at Spatial Modeling: From Attention to Convolution☆91Updated last year