Rethinking Classification Loss Designs for Person Re-identification with a Unified View

Cited by: 0|Bibtex|Views39
Other Links: arxiv.org

Abstract:

Person Re-identification (ReID) aims at matching a person of interest across images. In convolutional neural networks (CNNs) based approaches, loss design plays a role of metric learning which guides the feature learning process to pull closer features of the same identity and to push far apart features of different identities. In recen...More

Code:

Data:

Your rating :
0

 

Tags
Comments