Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
谢昕辰 98dfa1749b | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
mae.yml | 1 year ago | |
upernet_mae-base_fp16_8x2_512x512_160k_ade20k.py | 2 years ago | |
upernet_mae-base_fp16_512x512_160k_ade20k_ms.py | 2 years ago |
Masked Autoencoders Are Scalable Vision Learners
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 3x 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 pre-training and shows promising scaling behavior.
@article{he2021masked,
title={Masked autoencoders are scalable vision learners},
author={He, Kaiming and Chen, Xinlei and Xie, Saining and Li, Yanghao and Doll{\'a}r, Piotr and Girshick, Ross},
journal={arXiv preprint arXiv:2111.06377},
year={2021}
}
To use other repositories' pre-trained models, it is necessary to convert keys.
We provide a script beit2mmseg.py
in the tools directory to convert the key of MAE model from the official repo to MMSegmentation style.
python tools/model_converters/beit2mmseg.py ${PRETRAIN_PATH} ${STORE_PATH}
E.g.
python tools/model_converters/beit2mmseg.py https://dl.fbaipublicfiles.com/mae/pretrain/mae_pretrain_vit_base.pth pretrain/mae_pretrain_vit_base_mmcls.pth
This script convert model from PRETRAIN_PATH
and store the converted model in STORE_PATH
.
In our default setting, pretrained models could be defined below:
pretrained models | original models |
---|---|
mae_pretrain_vit_base_mmcls.pth | 'mae_pretrain_vit_base' |
Verify the single-scale results of the model:
sh tools/dist_test.sh \
configs/mae/upernet_mae-base_fp16_8x2_512x512_160k_ade20k.py \
upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth $GPUS --eval mIoU
Since relative position embedding requires the input length and width to be equal, the sliding window is adopted for multi-scale inference. So we set min_size=512, that is, the shortest edge is 512. So the multi-scale inference of config is performed separately, instead of '--aug-test'. For multi-scale inference:
sh tools/dist_test.sh \
configs/mae/upernet_mae-base_fp16_512x512_160k_ade20k_ms.py \
upernet_mae-base_fp16_8x2_512x512_160k_ade20k_20220426_174752-f92a2975.pth $GPUS --eval mIoU
Method | Backbone | Crop Size | pretrain | pretrain img size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|---|---|---|
UPerNet | ViT-B | 512x512 | ImageNet-1K | 224x224 | 16 | 160000 | 9.96 | 7.14 | 48.13 | 48.70 | config | model | log |
No Description
Python Markdown Shell Dockerfile other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》