CaUCD: Causal Unsupervised Change Detection (opens in new tab)

Current unsupervised change detection (UCD) methods face two key limitations: inaccurate pseudo-label generation and failure to account for land cover influence, resulting in unreliable change area predictions. Specifically, existing methods neglect the influence of context during the generation of pseudo-labels and the probability of different land cover changes when training change detection networks. To address these issues, we designed a causal UCD (CaUCD) framework, consisting of two net...