Shortcuts

MLP-Mixer: An all-MLP Architecture for Vision

Abstract

Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary. We present MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. “mixing” the per-location features), and one with MLPs applied across patches (i.e. “mixing” spatial information). When trained on large datasets, or with modern regularization schemes, MLP-Mixer attains competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-the-art models. We hope that these results spark further research beyond the realms of well established CNNs and Transformers.

Citation

@misc{tolstikhin2021mlpmixer,
      title={MLP-Mixer: An all-MLP Architecture for Vision},
      author={Ilya Tolstikhin and Neil Houlsby and Alexander Kolesnikov and Lucas Beyer and Xiaohua Zhai and Thomas Unterthiner and Jessica Yung and Andreas Steiner and Daniel Keysers and Jakob Uszkoreit and Mario Lucic and Alexey Dosovitskiy},
      year={2021},
      eprint={2105.01601},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Pretrain model

The pre-trained modles are converted from timm.

ImageNet-1k

Model Params(M) Flops(G) Top-1 (%) Top-5 (%) Config Download
Mixer-B/16* 59.88 12.61 76.68 92.25 config model
Mixer-L/16* 208.2 44.57 72.34 88.02 config model

Models with * are converted from other repos.

Read the Docs v: stable
Versions
latest
stable
Downloads
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.