Switchable Whitening for Deep Representation Learning

Info

• Conference: ICCV 2019
• Cites: 8
• Github Stars: 104
• Github Solved/Issue: 3/7
• Author:

Main Idea

• Next generation of IBN.
• Use covariance instead of variancce. Use whitening transformation instead of standardization.
• Make SW differetiable.
• 
• So different ratio for different task.
• 
• 
• Used by mmlab in

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 $Clusters + Pseudo Lable$, however a wrong pseudo lable usually have great bad effect on performance.

• So, they solve this with $Mutua$