52CV / WACV-2022-Papers
☆38Updated 2 years ago
Related projects: ⓘ
- A Pytorch Toy Implementation of 'Dynamic Region-Aware Convolution (ECCV2020)'☆102Updated 3 years ago
- MobileFormer in torch☆66Updated 3 years ago
- [CVPR 2022] TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing☆41Updated 2 years ago
- Official implementation for paper "LightViT: Towards Light-Weight Convolution-Free Vision Transformers"☆136Updated 2 years ago
- ☆130Updated last year
- This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures☆58Updated last year
- ☆26Updated 2 years ago
- Vision Transformers with Hierarchical Attention☆93Updated this week
- Masked Generative Distillation (ECCV 2022)☆208Updated last year
- ☆116Updated last year
- PyTorch implementation of the paper "Learning to Resize Images for Computer Vision Tasks" on Imagenette and Imagewoof datasets☆58Updated 3 years ago
- CVPR 2022 "Online Convolutional Re-parameterization"☆169Updated 2 years ago
- The official implementation of ELSA: Enhanced Local Self-Attention for Vision Transformer☆115Updated last year
- [TPAMI22] Pyramid Pooling Transformer for Scene Understanding☆198Updated last year
- ☆81Updated 3 years ago
- Official Implementation of ECCV2022 paper "OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers"☆87Updated last year
- ☆46Updated 3 years ago
- An official implementation of the PseCo (ECCV2022)☆133Updated 2 years ago
- ☆145Updated last year
- Cosine Annealing Warm Booting LR☆24Updated 2 years ago
- The code for the paper 'BA-Net: Bridge Attention for Deep Convolutional Neural Networks'☆25Updated 2 years ago
- 论文复现,多机多卡☆47Updated 2 years ago
- ☆54Updated 2 years ago
- CMT: Convolutional Neural Networks Meet Vision Transformers☆118Updated 2 years ago
- This is an unofficial implementation of BOAT: Bilateral Local Attention Vision Transformer☆53Updated 2 years ago
- ☆48Updated 2 years ago
- Unofficial implementation of Copy-Paste method:Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation☆132Updated 3 years ago
- Official implementation of the paper ``Unifying Nonlocal Blocks for Neural Networks'' (ICCV'21)☆96Updated 2 years ago
- Official implementation for "IoU-Enhanced Attention for End-to-End Task Specific Object Detection"☆17Updated last year
- Deep Networks with Recurrent Layer Aggregation☆28Updated 2 years ago