Unsupervised Domain Adaptive Person Re-id with Local-enhance and Prototype Dictionary Learning. (arXiv:2201.03803v1 [cs.CV])

The unsupervised domain adaptive person re-identification (re-ID) task has
been a challenge because, unlike the general domain adaptive tasks, there is no
overlap between the classes of source and target domain data in the person
re-ID, which leads to a significant domain gap. State-of-the-art unsupervised
re-ID methods train the neural networks using a memory-based contrastive loss.
However, performing contrastive learning by treating each unlabeled instance as
a class will lead to the problem of class collision, and the updating intensity …

arxiv cv dictionary learning person unsupervised