lucidrains / global-self-attention-network
A Pytorch implementation of Global Self-Attention Network, a fully-attention backbone for vision tasks
☆94Updated 4 years ago
Alternatives and similar repositories for global-self-attention-network:
Users that are interested in global-self-attention-network are comparing it to the libraries listed below
- Gated Channel Transformation for Visual Recognition (CVPR 2020)☆134Updated 4 years ago
- ☆74Updated 4 years ago
- Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones☆198Updated 3 years ago
- MLP-Like Vision Permutator for Visual Recognition (PyTorch)☆191Updated 2 years ago
- unofficial implementation of CondConv: Conditionally Parameterized Convolutions for Efficient Inference in PyTorch.☆156Updated last year
- A Pytorch implementation for the paper Local Relational Networks for Image Recognition (https://arxiv.org/pdf/1904.11491.pdf)☆113Updated 3 years ago
- Tensor Low-rank Reconstruction for Semantic Segmentation☆110Updated 4 years ago
- Dynamic Group Convolution for Accelerating Convolutional Neural Networks (ECCV 2020)☆128Updated 3 years ago
- (CVPR-Oral 2021) PyTorch implementation of Knowledge Evolution approach and Split-Nets☆83Updated 3 years ago
- Implementation of Convolutional enhanced image Transformer☆103Updated 3 years ago
- [Preprint] ConvMLP: Hierarchical Convolutional MLPs for Vision, 2021☆166Updated 2 years ago
- Implementation for Context-Gated Convolution☆59Updated 3 years ago
- official code for dynamic convolution decomposition☆131Updated 3 years ago
- This repo contains the code of "ConTNet: Why not use convolution and transformer at the same time?"☆97Updated 3 years ago
- PyTorch reimplementation of the paper "Involution: Inverting the Inherence of Convolution for Visual Recognition" (2D and 3D Involution) …☆105Updated 2 years ago
- ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks☆79Updated 4 years ago
- ☆191Updated 2 years ago
- Official Repsoitory for "Activate or Not: Learning Customized Activation." [CVPR 2021]☆203Updated 3 years ago
- ☆119Updated 2 years ago
- Official implementation of the paper ``Unifying Nonlocal Blocks for Neural Networks'' (ICCV'21)☆98Updated 2 years ago
- The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks☆215Updated 3 years ago
- This is an official implementation for "ResT: An Efficient Transformer for Visual Recognition".☆282Updated 2 years ago
- [T-IP 2023] Code for exponential adaptive pooling for PyTorch☆81Updated last year
- Vision Transformers with Hierarchical Attention☆99Updated 5 months ago
- Implementation of various Vision Transformers I found interesting☆84Updated 3 years ago
- Implementations of Recent Papers in Computer Vision☆39Updated 2 years ago
- [CVPR2022 - Oral] Official Jax Implementation of Learned Queries for Efficient Local Attention☆116Updated 2 years ago
- Filter Response Normalization Layer in PyTorch☆121Updated 5 years ago
- Code for “Disentangled Non-local Neural Networks”☆109Updated 4 years ago
- Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)☆330Updated 4 years ago