lucidrains / deformable-attentionLinks
Implementation of Deformable Attention in Pytorch from the paper "Vision Transformer with Deformable Attention"
☆344Updated 4 months ago
Alternatives and similar repositories for deformable-attention
Users that are interested in deformable-attention are comparing it to the libraries listed below
Sorting:
- [ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"☆358Updated last year
- Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Atte…☆873Updated last year
- InceptionNeXt: When Inception Meets ConvNeXt (CVPR 2024)☆307Updated 6 months ago
- MetaFormer Baselines for Vision (TPAMI 2024)☆472Updated last year
- Lite Vision Transformer (CVPR 2022)☆143Updated 2 years ago
- [ICCV 2023] You Only Look at One Partial Sequence☆342Updated last year
- Official Code of Paper "Reversible Column Networks" "RevColv2"☆263Updated last year
- [NeurIPS 2022] Official code for "Focal Modulation Networks"☆736Updated last year
- Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022☆1,122Updated last year
- PyTorch reimplementation of the paper "MaxViT: Multi-Axis Vision Transformer" [ECCV 2022].☆163Updated last year
- CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022☆570Updated last year
- ConvMAE: Masked Convolution Meets Masked Autoencoders☆507Updated 2 years ago
- ☆190Updated 2 years ago
- [CVPR 2024] Deformable Convolution v4☆642Updated last year
- [ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer☆327Updated 4 months ago
- [ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers…☆274Updated last year
- [NeurIPS 2022] HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions☆337Updated last year
- Official implementation of CrossViT. https://arxiv.org/abs/2103.14899☆395Updated 3 years ago
- ☆216Updated 3 years ago
- Official repository of Slide-Transformer (CVPR2023)☆171Updated 9 months ago
- Official repository of FLatten Transformer (ICCV2023)☆432Updated 7 months ago
- iFormer: Inception Transformer☆247Updated 2 years ago
- [CVPR 2022 Oral] Official implementation of DN-DETR☆571Updated last year
- Official MegEngine implementation of RepLKNet☆277Updated 3 years ago
- MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022☆581Updated 2 years ago
- Code Release for MViTv2 on Image Recognition.☆427Updated 6 months ago
- [ICLR 2022] Official implementation of the paper "DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR"☆550Updated 2 years ago
- [ICLR'22 Oral] Implementation of "CycleMLP: A MLP-like Architecture for Dense Prediction"☆288Updated 3 years ago
- [CVPR 2022] MPViT:Multi-Path Vision Transformer for Dense Prediction☆378Updated 3 years ago
- This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org…☆375Updated 2 years ago