Invariant and consistent: Unsupervised representation learning for few-shot visual recognition

Few-shot visual recognition aims to identify novel unseen classes with few labels while learning gener-alized prior knowledge from base classes. Recent ideas propose to explore this problem in an unsuper-vised setting, i.e., without any labels in base classes, which reduces the heavy consumption of manual annotations. In this paper, we build upon a self-supervised insight and propose a novel unsupervised learning approach that joints Invariant and Consistent (InCo) representation for the few-shot task. For the invariant representation operation, we present a geometric invariance module to construct the rota-tion prediction of each instance, which learns the intra-instance variance and improves the feature dis-crimination. To further build consistency representation of inter-instance, we propose a pairwise consistency module from two contrastive learning aspects: a holistic contrastive learning with historical training queues, and a local contrastive learning for enhancing the representation of current training samples. Moreover, to better facilitate contrastive learning among features, we introduce an asymmetric convolutional architecture to encode high-quality representations. Comprehensive experiments on 4 public benchmarks demonstrate the utility of our approach and the superiority compared to existing approaches.(c) 2022 Elsevier B.V. All rights reserved.