DeLightCMU / PSALinks
This is an official implementation of "Polarized Self-Attention: Towards High-quality Pixel-wise Regression"
☆254Updated 4 years ago
Alternatives and similar repositories for PSA
Users that are interested in PSA are comparing it to the libraries listed below
Sorting:
- [ NeurIPS2021] This is an official implementation of our paper "HRFormer: High-Resolution Transformer for Dense Prediction".☆519Updated 3 years ago
- Bottleneck Transformers for Visual Recognition☆280Updated 4 years ago
- [ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction☆208Updated 4 years ago
- RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features (CVPR 2021)☆223Updated 3 years ago
- This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures☆69Updated 2 years ago
- This is an official implementation for "ResT: An Efficient Transformer for Visual Recognition".☆289Updated 3 years ago
- [ECCV-2020-oral]-Semantic Flow for Fast and Accurate Scene Parsing☆381Updated last year
- code for `Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation`☆187Updated 2 years ago
- [TIP 2022] CBNetV2: A Composite Backbone Network Architecture for Object Detection☆392Updated last year
- [ICCV 2021] Code for approximated exponential maximum pooling☆298Updated 2 years ago
- ☆195Updated 2 years ago
- TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022☆403Updated 3 years ago
- SOTR: Segmenting Objects with Transformers☆193Updated 3 years ago
- HyperSeg - Official PyTorch Implementation☆214Updated 2 years ago
- ☆280Updated 4 years ago
- ISTR: End-to-End Instance Segmentation with Transformers (https://arxiv.org/abs/2105.00637)☆209Updated last year
- Depthwise Over-parameterized Convolutional Layer☆198Updated 2 years ago
- E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation☆227Updated last year
- Official MegEngine implementation of RepLKNet☆282Updated 3 years ago
- This is an official implementation for "Contextual Transformer Networks for Visual Recognition".☆537Updated 4 years ago
- Code for our ICASSP 2021 paper: SA-Net: Shuffle Attention for Deep Convolutional Neural Networks☆263Updated 4 years ago
- ☆194Updated 4 years ago
- [NeurIPS 2022] HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions☆342Updated last year
- Unofficial implementation of Copy-Paste method:Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation☆137Updated 4 years ago
- [CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction☆386Updated 3 years ago
- The official implementation of "Rethink Dilated Convolution for Real-time Semantic Segmentation"☆89Updated last year
- [ECCV 2020] Boundary-preserving Mask R-CNN☆198Updated 5 years ago
- Code and models for mobile-former☆131Updated 3 years ago
- [ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"☆355Updated 2 years ago
- ☆209Updated 3 years ago