Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning

arXiv:2401.01598v2 Announce Type: replace
Abstract: Few-shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes based on very limited training data without forgetting the old ones encountered. Existing studies solely relied on pure visual networks, while in this paper we solved FSCIL by leveraging the Vision-Language model (e.g., CLIP) and propose a simple yet effective framework, named Learning Prompt with Distribution-based Feature Replay (LP-DiF). We observe that simply using CLIP for zero-shot evaluation can substantially outperform the most influential methods. …

arxiv class cs.cv distribution feature few-shot incremental prompt type