Cross-Domain Incremental Image Classification via Domain-Specific Prototypes and Contrastive Learning

Remote sensing models in incremental learning scenarios often need to contend with both the newly emerged classes and cross-domain feature shifts, a combined challenge that we name it as Cross-Domain Incremental Learning (CDIL). Existing approaches typically address Class-Incremental Learning (CIL) or Domain-Incremental Learning (DIL) separately, failing to effectively handle recurring classes across domain shifts and leading to catastrophic forgetting or misaligned features across domains. To address this gap, we propose a novel CDIL framework that integrates a frozen pre-trained backbone with domain-specific adapter modules and domain-specific prototype construction. This architecture preserves general feature representations while capturing domain-specific nuances via lightweight adapters, and it stores class prototypes from each domain to unify knowledge of recurring classes. We further introduce multi-level supervised contrastive losses to ensure consistent class representation across domains. Extensive experiments on multiple remote sensing image classification benchmarks demonstrate that the proposed method significantly outperforms state-of-the-art CIL and DIL strategies, achieving superior accuracy and retention of old knowledge under severe domain shifts. The code will be released.