Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
Info
Conference: ICLR 2020
Cites: 6
Github Stars: 211
Github Solved/Issue: 22/26
Author:
Main Idea
Method for Unsupervised DA on Person Re-ID. [Person re-identification (re-ID) aims at identifying the same persons’ images across different cameras. However, domain diversities between different datasets pose an evident challenge for adapting the re-ID model trained on one dataset to another one.]
Traditional methods usually use Clusters+PseudoLable, however a wrong pseudo lable usually have great bad effect on performance.
So, they solve this with MutualLearning+MovingAverageModel