AI RESEARCH
MILE: Mixture of Incremental LoRA Experts for Continual Semantic Segmentation across Domains and Modalities
arXiv CS.CV
•
ArXi:2605.03555v1 Announce Type: new Continual semantic segmentation requires models to adapt to new domains or modalities without sacrificing performance on previously learned tasks. Expert-based learning, in which task-specific modules specialize in different domains, has proven effective in mitigating forgetting. These methods include dynamic expansion, which suffers from scalability issues, or parameter isolation, which constrains the ability to learn new tasks. We