Conference
Open access
Sep 2026
RACL: reliability-aware contrastive learning for weakly supervised change detection
An end-to-end framework for weakly supervised change detection is proposed that effectively improves weakly supervised change detection performance and introduces a Reliability-Aware Contrastive Learning strategy to enhance the separability of change representations.
Die-Die Liu, Si-Bao Chen
· Journal of Physics, Conferen... · 0 citations