Skip to content
/ PSA Public

This is an official implementation of "Polarized Self-Attention: Towards High-quality Pixel-wise Regression"

License

Notifications You must be signed in to change notification settings

DeLightCMU/PSA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 

Repository files navigation

Polarized Self-Attention: Towards High-quality Pixel-wise Regression

This is an official implementation of:

Huajun Liu, Fuqiang Liu, Xinyi Fan and Dong Huang. Polarized Self-Attention: Towards High-quality Pixel-wise Regression Arxiv Version

PWC PWC PWC

Citation:

@article{Liu2021PSA,
  title={Polarized Self-Attention: Towards High-quality Pixel-wise Regression},
  author={Huajun Liu and Fuqiang Liu and Xinyi Fan and Dong Huang},
  journal={Arxiv Pre-Print arXiv:2107.00782 },
  year={2021}
}

Codes and Pre-trained models will be uploaded soon~

Top-down 2D pose estimation models pre-trained on the MS-COCO keypoint task(Table4 in the Arxiv version).

Model Name Backbone Input Size AP pth file
UDP-Pose-PSA(p) HRNet-W48 256x192 78.9 to be uploaded
UDP-Pose-PSA(p) HRNet-W48 384x288 79.5 to be uploaded
UDP-Pose-PSA(s) HRNet-W48 384x288 79.4 to be uploaded

Setup and inference:

Semantic segmentation models pre-trained on Cityscapes (Table5 in the Arxiv version).

Model Name Backbone val mIoU pth file
HRNetV2-OCR+PSA(p) HRNetV2-W48 86.95 download
HRNetV2-OCR+PSA(s) HRNetV2-W48 86.72 download

Setup and inference:

About

This is an official implementation of "Polarized Self-Attention: Towards High-quality Pixel-wise Regression"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages