SAM-driven MAE pre-training and background-aware meta-learning for unsupervised vehicle re-identification
Sign Up to like & getrecommendations! Published in 2024 at "Computational Visual Media"
DOI: 10.1007/s41095-024-0424-2
Abstract: Distinguishing identity-unrelated background information from discriminative identity information poses a challenge in unsupervised vehicle re-identification (Re-ID). Re-ID models suffer from varying degrees of background interference caused by continuous scene variations. The recently proposed segment anything… read more here.
Keywords: unsupervised vehicle; vehicle; mae pre; sam driven ... See more keywords