SPIresearch / UTR

Code for paper "Source Data and Target Annotations Agnostic Transferability Representation for Source-Free Unsupervised Domain Adaptation"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

UTR

Code for paper "Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation".

Train source model

python train_source.py

Adapt to target domain

python caf.py

Acknowledgement

The codes are based on SHOT (ICML 2020): https://github.com/tim-learn/SHOT.

About

Code for paper "Source Data and Target Annotations Agnostic Transferability Representation for Source-Free Unsupervised Domain Adaptation"


Languages

Language:Python 100.0%