Alternatives and similar repositories for EfficientFormer

Users that are interested in EfficientFormer are comparing it to the libraries listed below

• sail-sg / poolformer
  PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)
  ☆1,351Updated last year
• sail-sg / metaformer
  MetaFormer Baselines for Vision (TPAMI 2024)
  ☆484Updated last year
• apple / ml-mobileone
  This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone" CVPR 2023.
  ☆804Updated 3 years ago
• DingXiaoH / RepLKNet-pytorch
  Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)
  ☆928Updated last year
• chinhsuanwu / mobilevit-pytorch
  A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"
  ☆543Updated 3 years ago
• huawei-noah / VanillaNet
  ☆824Updated last year
• microsoft / Cream
  This is a collection of our NAS and Vision Transformer work.
  ☆1,801Updated last year
• microsoft / FocalNet
  [NeurIPS 2022] Official code for "Focal Modulation Networks"
  ☆741Updated last year
• facebookresearch / ConvNeXt-V2
  Code release for ConvNeXt V2 model
  ☆1,824Updated last year
• apple / ml-cvnets
  CVNets: A library for training computer vision networks
  ☆1,914Updated last year
• facebookresearch / LeViT
  LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference
  ☆617Updated 3 years ago
• NVlabs / FasterViT
  [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
  ☆877Updated last month
• czczup / ViT-Adapter
  [ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
  ☆1,409Updated 3 months ago
• microsoft / CSWin-Transformer
  CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped, CVPR 2022
  ☆581Updated last year
• facebookresearch / MaskFormer
  Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)
  ☆1,429Updated 3 years ago
• google-research / maxvit
  [ECCV 2022] Official repository for "MaxViT: Multi-Axis Vision Transformer". SOTA foundation models for classification, detection, segmen…
  ☆484Updated 2 years ago
• SHI-Labs / Neighborhood-Attention-Transformer
  Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022
  ☆1,145Updated last year
• NVlabs / GCVit
  [ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
  ☆438Updated last year
• microsoft / CvT
  This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.
  ☆582Updated 2 years ago
• mmaaz60 / EdgeNeXt
  [CADL'22, ECCVW] Official repository of paper titled "EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Ap…
  ☆388Updated 2 years ago
• whai362 / PVT
  Official implementation of PVT series
  ☆1,845Updated 2 years ago
• dingmyu / davit
  [ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"
  ☆363Updated last year
• Sense-X / UniFormer
  [ICLR2022] official implementation of UniFormer
  ☆877Updated last year
• Visual-Attention-Network / SegNeXt
  Official Pytorch implementations for "SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation" (NeurIPS 2022)
  ☆846Updated 2 years ago
• LeapLabTHU / DAT
  Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Atte…
  ☆896Updated last year
• chinhsuanwu / coatnet-pytorch
  A PyTorch implementation of "CoAtNet: Marrying Convolution and Attention for All Data Sizes"
  ☆389Updated 3 years ago
• locuslab / convmixer
  Implementation of ConvMixer for "Patches Are All You Need? 🤷"
  ☆1,077Updated 2 years ago
• NVlabs / FAN
  Official PyTorch implementation of Fully Attentional Networks
  ☆479Updated 2 years ago
• microsoft / SimMIM
  This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".
  ☆991Updated 2 years ago
• facebookresearch / ToMe
  A method to increase the speed and lower the memory footprint of existing vision transformers.
  ☆1,089Updated last year