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

TL;DR

SENet introduces spectral filtering of exemplars with a shrinkage loss to improve class representation in few-shot learning, outperforming traditional prototype methods.

Contribution

The paper proposes Shrinkage Exemplar Networks (SENet), a novel approach that uses spectral filtering and a shrinkage loss to better represent classes in few-shot learning.

Findings

Effective on miniImageNet, tiered-ImageNet, CIFAR-FS datasets

Outperforms traditional prototype-based methods

Improves class representation accuracy

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 SENet, categories are represented by the embedding of samples that shrink towards their mean via spectral filtering. Furthermore, a shrinkage exemplar loss is proposed to replace the widely used cross entropy loss for capturing the information of individual shrinkage samples. Several experiments were conducted on miniImageNet, tiered-ImageNet and CIFAR-FS datasets. The experimental results demonstrate the effectiveness of our proposed method.