d-li14 / involution
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
☆1,307Updated 3 years ago
Alternatives and similar repositories for involution:
Users that are interested in involution are comparing it to the libraries listed below
- (ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"☆1,092Updated 2 years ago
- Deformable ConvNets V2 (DCNv2) in PyTorch☆1,460Updated 2 years ago
- Official implementation of PVT series☆1,795Updated 2 years ago
- ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks☆841Updated 2 years ago
- RepVGG: Making VGG-style ConvNets Great Again☆3,384Updated 2 years ago
- ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet☆1,185Updated last year
- Exploring Self-attention for Image Recognition, CVPR2020.☆753Updated 4 years ago
- Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks☆1,320Updated 3 years ago
- ResNeSt: Split-Attention Networks☆3,255Updated 2 years ago
- GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond☆1,204Updated 4 years ago
- Implementation of the Swin Transformer in PyTorch.☆822Updated 4 years ago
- CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).☆1,457Updated 4 years ago
- Two simple and effective designs of vision transformer, which is on par with the Swin transformer☆599Updated 2 years ago
- PyTorch implementation of SENet☆2,318Updated 4 years ago
- Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"☆2,133Updated 2 years ago
- Implementation of Non-local Block.☆1,572Updated 2 years ago
- PyTorch implementation of Deformable ConvNets v2 (Modulated Deformable Convolution)☆756Updated 6 years ago
- Code for our CVPR2021 paper coordinate attention☆1,048Updated 3 years ago
- a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results☆863Updated 4 years ago
- [CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers☆747Updated 3 years ago
- PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)☆1,324Updated 10 months ago
- Dual Attention Network for Scene Segmentation (CVPR2019)☆2,428Updated 3 months ago
- PyTorch implementation of EfficientNetV2 family☆470Updated 3 years ago
- Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute☆1,531Updated 4 years ago
- Deformable Convolutional Networks v2 with Pytorch☆1,301Updated 11 months ago
- [CVPR2020] GhostNet: More Features from Cheap Operations☆528Updated 4 years ago
- Implementing Attention Augmented Convolutional Networks using Pytorch☆650Updated 3 years ago
- Implementation of Bottleneck Transformer in Pytorch☆678Updated 3 years ago
- Gradually-Warmup Learning Rate Scheduler for PyTorch☆988Updated 6 months ago
- Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)☆905Updated 11 months ago