SENet: A Spectral Filtering Approach to Represent Exemplars for Few-shot Learning

arXiv:2305.18970v2 Announce Type: replace
Abstract: Prototype is widely used to represent internal structure of category for few-shot learning, which was proposed as a simple inductive bias to address the issue of overfitting. However, since prototype representation is normally averaged from individual samples, it can appropriately to represent some classes but with underfitting to represent some others that can be batter represented by exemplars. To address this problem, in this work, we propose Shrinkage Exemplar Networks (SENet) for few-shot classification. In …

abstract arxiv bias cs.cv few-shot few-shot learning filtering inductive issue normally overfitting representation samples simple type