Few-Shot Class-Incremental Learning with Prior Knowledge
CoRR(2024)
摘要
To tackle the issues of catastrophic forgetting and overfitting in few-shot
class-incremental learning (FSCIL), previous work has primarily concentrated on
preserving the memory of old knowledge during the incremental phase. The role
of pre-trained model in shaping the effectiveness of incremental learning is
frequently underestimated in these studies. Therefore, to enhance the
generalization ability of the pre-trained model, we propose Learning with Prior
Knowledge (LwPK) by introducing nearly free prior knowledge from a few
unlabeled data of subsequent incremental classes. We cluster unlabeled
incremental class samples to produce pseudo-labels, then jointly train these
with labeled base class samples, effectively allocating embedding space for
both old and new class data. Experimental results indicate that LwPK
effectively enhances the model resilience against catastrophic forgetting, with
theoretical analysis based on empirical risk minimization and class distance
measurement corroborating its operational principles. The source code of LwPK
is publicly available at: .
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要