Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning

arXiv:2405.04918v1 Announce Type: new
Abstract: Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods address catastrophic forgetting and overfitting by freezing the feature extractor during novel-class learning. However, these methods usually tend to cause the confusion between base and novel classes, i.e., classifying novel-class samples into base classes. In this paper, we delve into this phenomenon to study its cause and solution. We first interpret the confusion …

abstract arxiv catastrophic forgetting class cs.ai cs.cv exploration feature few-shot however incremental incremental learning information knowledge novel overfitting redundancy samples type while