Learning Multi-level Weight-centric Features for Few-shot Learning

TL;DR

This paper introduces a multi-level weight-centric feature learning approach for few-shot learning, enhancing feature representation and weight generation to improve classification performance with limited samples.

Contribution

It proposes a novel multi-level feature learning method with a weight-centric training strategy, addressing both representation power and weight generation capacity in few-shot learning.

Findings

Significantly outperforms existing methods on low-shot benchmarks.

Improves transferability and discriminative ability of features.

Effective across various network backbones.

Abstract

Few-shot learning is currently enjoying a considerable resurgence of interest, aided by the recent advance of deep learning. Contemporary approaches based on weight-generation scheme delivers a straightforward and flexible solution to the problem. However, they did not fully consider both the representation power for unseen categories and weight generation capacity in feature learning, making it a significant performance bottleneck. This paper proposes a multi-level weight-centric feature learning to give full play to feature extractor's dual roles in few-shot learning. Our proposed method consists of two essential techniques: a weight-centric training strategy to improve the features' prototype-ability and a multi-level feature incorporating a mid- and relation-level information. The former increases the feasibility of constructing a discriminative decision boundary based on a few samples. Simultaneously, the latter helps improve the transferability for characterizing novel classes and preserve classification capability for base classes. We extensively evaluate our approach to low-shot classification benchmarks. Experiments demonstrate our proposed method significantly outperforms its counterparts in both standard and generalized settings and using different network backbones.