This repository is the official implementation of “Denoising Masked Autoencoders Help Robust Classification”, based on the official implementation of MAE in PyTorch.
@Article{dmae2022,
author = {Quanlin Wu and Hang Ye, Yuntian Gu and Huishuai Zhang, Liwei Wang and Di He},
journal = {arXiv:2210.06983},
title = {Denoising Masked Autoencoders Are Certifiable Robust Vision Learners},
year = {2022},
}
The pre-training instruction is in PRETRAIN.md.
The following table provides the pre-trained checkpoints used in the paper:
| Model | Size | Epochs | Link |
|---|---|---|---|
| DMAE-Base | 427MB | 1100 | download |
| DMAE-Large | 1.23GB | 1600 | download |
The fine-tuning and evaluation instruction is in FINETUNE.md.
This project is under the CC-BY-NC 4.0 license. See LICENSE for details.