Learning multi-level weight-centric features for few-shot learning

•We propose a weight-centric learning strategy that helps reduce the interclass variance of novel-class data.•We propose a multi-level feature learning framework, which demonstrates its strong prototype-ability and transferability even in a cross-task environment for few-shot learning.•We extensively evaluate our approach on two low-shot classification benchmarks in both standard and generalized FSL learning settings. Our results show that the mid-level features exhibit strong transferability even in a cross-task environment while the relation-level features help preserve base-class accuracy in the generalized FSL setting. 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.