ResMLP: Feedforward networks for image classification with data-efficient training

Code

• github.com/lucidrains/res-mlp-pytorch
  pytorch★ 201
• github.com/lalithjets/surgical_vqa
  pytorch★ 63
• github.com/rishikksh20/ResMLP-pytorch
  pytorch★ 45
• github.com/leaderj1001/Bag-of-MLP
  pytorch★ 20
• github.com/jaketae/res-mlp
  pytorch★ 3
• github.com/MindCode-4/code-13/tree/main/res_mlp_ms
  mindspore★ 0
• github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/mlp_family
  tf★ 0
• github.com/megvii-research/basecls/tree/main/zoo/public/resmlp
  none★ 0
• github.com/yeyinthtoon/tf2-resmlp
  tf★ 0
• github.com/MindCode-4/code-8/tree/main/res_mlp_ms
  mindspore★ 0

Abstract

We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically across channels, and (ii) a two-layer feed-forward network in which channels interact independently per patch. When trained with a modern training strategy using heavy data-augmentation and optionally distillation, it attains surprisingly good accuracy/complexity trade-offs on ImageNet. We also train ResMLP models in a self-supervised setup, to further remove priors from employing a labelled dataset. Finally, by adapting our model to machine translation we achieve surprisingly good results. We share pre-trained models and our code based on the Timm library.

Tasks

Benchmark Results

Reproductions