HSONet:A Siamese foreground association-driven hard case sample optimization network for high-resolution remote sensing image change detection

arXiv:2402.16242v1 Announce Type: new
Abstract: In the later training stages, further improvement of the models ability to determine changes relies on how well the change detection (CD) model learns hard cases; however, there are two additional challenges to learning hard case samples: (1) change labels are limited and tend to pointer only to foreground targets, yet hard case samples are prevalent in the background, which leads to optimizing the loss function focusing on the foreground targets and ignoring the background …

abstract arxiv association case cases challenges change cs.ai cs.cv detection image improvement network optimization sample samples sensing training type