AI RESEARCH
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
arXiv CS.LG
•
ArXi:2605.28809v1 Announce Type: cross Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g., ``a photo of a [CLASS]''. This seemingly monolithic matching process can be decomposed into two conceptually distinct stages: attribute extraction and attribute aggregation. For example, a model may recognize cat using attributes such as fur texture and whiskers.