Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift

arXiv:2403.14114v1 Announce Type: new
Abstract: Person re-identification (re-id), which aims to retrieve images of the same person in a given image from a database, is one of the most practical image recognition applications. In the real world, however, the environments that the images are taken from change over time. This causes a distribution shift between training and testing and degrades the performance of re-id. To maintain re-id performance, models should continue adapting to the test environment's temporal changes. Test-time adaptation …

abstract applications arxiv change cs.cv database distribution environments however identification image image recognition images person practical recognition shift temporal test type world