Skip to content

TF2.x implementation of PixPro (Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021).

Notifications You must be signed in to change notification settings

PaperCodeReview/PixPro-TF

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PixPro-TF

This is an unofficial implementation of Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021.

Requirements

(TODO : requirements.txt and Dockerfile for the image of fixed environment.)

  • python >= 3.6
  • tensorflow >= 2.2

Training

TODO

  • LARS optimizer
  • Downstream
    • Object Detection
    • Semantic Segmentation
    • Instance Segmentation
    • Semi-Supervised Object Detection
    • Linear Evaluation

Evaluation

TODO

Results

TODO

Citation

@article{Xie2020PropagateYE,
  title={Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning},
  author={Zhenda Xie and Yutong Lin and Zheng Zhang and Yue Cao and Stephen Lin and Han Hu},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.10043}
}

About

TF2.x implementation of PixPro (Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021).

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages