Skip to content
/ CEMA Public

[ICLR 2024] Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation

License

Notifications You must be signed in to change notification settings

chenyaofo/CEMA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation

This is the official project repository for Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation [ICLR 2024], Authors: Yaofo Chen, Shuaicheng Niu, Yaowei Wang, Shoukai Xu, Hengjie Song, Mingkui Tan

Dependencies Installation:

Please refer to requirements.txt

Data Preparation:

Please download ImageNet-C and extract the tar files. Then use tools/make_tfrec.py to transfer raw image files into tfrecord format.

Example: ImageNet-C Experiments

python -m entry.run --conf conf/cema.conf -o outputs/

Citation

@inproceedings{chen2024towards,
  title={Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation},
  author={Yaofo Chen and Shuaicheng Niu and Shoukai Xu and Hengjie Song and Yaowei Wang and Mingkui Tan},
  booktitle={International Conference on Learning Representations},
  year={2024},
}

About

[ICLR 2024] Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages