Skip to content

Official implementation of "Any Region Can Be Perceived Equally and Effectively on Rotation Pretext Task Using Full Rotation and Weighted-Region Mixture"

License

Notifications You must be signed in to change notification settings

anthonyweidai/FullRot_WRMix

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FullRot_WRMix

The official implementation of FullRot + WRMix provides a comprehensive set of functions for deep learning and computer vision tasks. It includes training process printing, log saving, and computation and storage of standard metrics for classification, semantic segmentation, and object detection tasks.

Any region can be perceived equally and effectively on rotation pretext task using full rotation and weighted-region mixture
Wei Dai, Tianyi Wu, Rui Liu, Min Wang, Jianqin Yin, Jun Liu
Accepted in Neural Networks, 2024. [SSRN][Paper]

Installation

For instructions on how to install the FullRot_WRMix implementation, please refer to the INSTALL.md file.

Benchmark and Evaluation

To prepare the datasets required for benchmark evaluation and training, please consult the DATA.md file.

For pre-training the resnet50 model using self-supervised learning, you can follow the settings provided in main.sh script. Additionally, we provide downstream task training settings in the downstream_example.sh script.

Classification results on STL-10, CIFAR-10/100, Sports-100, Mammals-45, and PAD-UFES-20

Semantic segmentation results on PASCAL VOC 2012, ISIC 2018, FloodArea, and TikTokDances

Object Detection results on PASCAL VOC 2007 and UTDAC 2020

Ablation study

For the training settings of the ablation study and extracurricular experiments, please refer to the ablation.sh and ablation_extra.sh scripts.

Citation

If you find this implementation useful in your research, we kindly request that you consider citing our paper as follows:

@article{dai2024any,
  title={Any region can be perceived equally and effectively on rotation pretext task using full rotation and weighted-region mixture},
  author={Dai, Wei and Wu, Tianyi and Liu, Rui and Wang, Min and Yin, Jianqin and Liu, Jun},
  journal={Neural Networks},
  pages={106350},
  year={2024},
  publisher={Elsevier}
}

About

Official implementation of "Any Region Can Be Perceived Equally and Effectively on Rotation Pretext Task Using Full Rotation and Weighted-Region Mixture"

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published