AI RESEARCH

Effective Prompt Pool Learning for Continual Category Discovery

arXiv CS.CV

ArXi:2407.19001v3 Announce Type: replace This paper studies effective prompt pool learning for Continual Category Discovery (CCD), a challenging open-world setting where a model must discover novel categories from a continuous stream of unlabelled data containing both known and novel classes, while mitigating catastrophic forgetting of previously learned concepts. We