Enhanced Few-Shot Class-Incremental Learning via Ensemble Models

arXiv:2401.07208v2 Announce Type: replace
Abstract: Few-shot class-incremental learning (FSCIL) aims to continually fit new classes with limited training data, while maintaining the performance of previously learned classes. The main challenges are overfitting the rare new training samples and forgetting old classes. While catastrophic forgetting has been extensively studied, the overfitting problem has attracted less attention in FSCIL. To tackle overfitting challenge, we design a new ensemble model framework cooperated with data augmentation to boost generalization. In this way, the enhanced …

abstract arxiv catastrophic forgetting challenges class cs.cv data ensemble few-shot incremental overfitting performance samples training training data type via