MAE — MMPretrain 1.2.0 documentation (original) (raw)

Abstract¶

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core designs. First, we develop an asymmetric encoder-decoder architecture, with an encoder that operates only on the visible subset of patches (without mask tokens), along with a lightweight decoder that reconstructs the original image from the latent representation and mask tokens. Second, we find that masking a high proportion of the input image, e.g., 75%, yields a nontrivial and meaningful self-supervisory task. Coupling these two designs enables us to train large models efficiently and effectively: we accelerate training (by 3× or more) and improve accuracy. Our scalable approach allows for learning high-capacity models that generalize well: e.g., a vanilla ViT-Huge model achieves the best accuracy (87.8%) among methods that use only ImageNet-1K data. Transfer performance in downstream tasks outperforms supervised pretraining and shows promising scaling behavior.

How to use it?¶

from mmpretrain import inference_model

predict = inference_model('vit-base-p16_mae-300e-pre_8xb128-coslr-100e_in1k', 'demo/bird.JPEG') print(predict['pred_class']) print(predict['pred_score'])

Models and results¶

Pretrained models¶

Image Classification on ImageNet-1k¶

Citation¶

@article{He2021MaskedAA, title={Masked Autoencoders Are Scalable Vision Learners}, author={Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Doll'ar and Ross B. Girshick}, journal={arXiv}, year={2021} }