Alternatives and similar repositories for deformable-attention

Users that are interested in deformable-attention are comparing it to the libraries listed below

• LeapLabTHU / DAT
  Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Atte…
  ☆912Updated last year
• dingmyu / davit
  [ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"
  ☆371Updated last year
• sail-sg / metaformer
  MetaFormer Baselines for Vision (TPAMI 2024)
  ☆494Updated last year
• SHI-Labs / Neighborhood-Attention-Transformer
  Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022
  ☆1,160Updated last year
• ChristophReich1996 / MaxViT
  PyTorch reimplementation of the paper "MaxViT: Multi-Axis Vision Transformer" [ECCV 2022].
  ☆164Updated 2 years ago
• Alpha-VL / ConvMAE
  ConvMAE: Masked Convolution Meets Masked Autoencoders
  ☆519Updated 2 years ago
• Amshaker / SwiftFormer
  [ICCV'23] Official repository of paper SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applicatio…
  ☆298Updated 4 months ago
• LeapLabTHU / Slide-Transformer
  Official repository of Slide-Transformer (CVPR2023)
  ☆173Updated last year
• ma-xu / Context-Cluster
  [ICLR 2023 Oral] Image as Set of Points
  ☆573Updated last year
• megvii-research / RevCol
  Official Code of Paper "Reversible Column Networks" "RevColv2"
  ☆264Updated 2 years ago
• ShoufaChen / CycleMLP
  [ICLR'22 Oral] Implementation of "CycleMLP: A MLP-like Architecture for Dense Prediction"
  ☆291Updated 3 years ago
• Chenglin-Yang / LVT
  Lite Vision Transformer (CVPR 2022)
  ☆145Updated 3 years ago
• raoyongming / HorNet
  [NeurIPS 2022] HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
  ☆343Updated last year
• OpenGVLab / DCNv4
  [CVPR 2024] Deformable Convolution v4
  ☆689Updated last year
• microsoft / FocalNet
  [NeurIPS 2022] Official code for "Focal Modulation Networks"
  ☆742Updated 2 years ago
• EPFL-VILAB / MultiMAE
  MultiMAE: Multi-modal Multi-task Masked Autoencoders, ECCV 2022
  ☆608Updated 2 years ago
• sail-sg / inceptionnext
  InceptionNeXt: When Inception Meets ConvNeXt (CVPR 2024)
  ☆339Updated last year
• microsoft / CSWin-Transformer
  CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022
  ☆585Updated 2 years ago
• fudan-zvg / GSS
  [CVPR 2023] Official repository of Generative Semantic Segmentation
  ☆221Updated 2 years ago
• ChristophReich1996 / Swin-Transformer-V2
  PyTorch reimplementation of the paper "Swin Transformer V2: Scaling Up Capacity and Resolution" (CVPR 2022)
  ☆205Updated 3 years ago
• OliverRensu / Shunted-Transformer
  ☆216Updated 3 years ago
• sail-sg / iFormer
  iFormer: Inception Transformer
  ☆247Updated 2 years ago
• VITA-Group / SLaK
  [ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers…
  ☆282Updated 2 years ago
• HDETR / H-Deformable-DETR
  [CVPR2023] This is an official implementation of paper "DETRs with Hybrid Matching".
  ☆275Updated 2 years ago
• Meituan-AutoML / CPVT
  ☆193Updated 2 years ago
• fudan-zvg / SeaFormer
  [ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer
  ☆346Updated 9 months ago
• NVlabs / GCVit
  [ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
  ☆441Updated last year
• ViTAE-Transformer / QFormer
  The official repo for [TPAMI'23] "Vision Transformer with Quadrangle Attention"
  ☆224Updated 2 months ago
• Sense-X / MixMIM
  MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning
  ☆146Updated 2 years ago
• IBM / CrossViT
  Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
  ☆412Updated 3 years ago