Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning

TL;DR

This paper introduces a novel training approach for few-shot learning that jointly enforces invariance and equivariance to geometric transformations, leading to improved generalization to new classes with limited data.

Contribution

It proposes a unique joint optimization of invariance and equivariance in feature learning for few-shot learning, which has not been explored before.

Findings

Outperforms state-of-the-art FSL methods on five benchmarks

Joint invariance and equivariance improve feature robustness

Self-supervised distillation further enhances performance

Abstract

In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning (FSL) is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. FSL tasks have been predominantly solved by leveraging the ideas from gradient-based meta-learning and metric learning approaches. However, recent works have demonstrated the significance of powerful feature representations with a simple embedding network that can outperform existing sophisticated FSL algorithms. In this work, we build on this insight and propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations. Equivariance or invariance has been employed standalone in the previous works; however, to the best of our knowledge, they have not been used jointly. Simultaneous optimization for both of these contrasting objectives allows the model to jointly learn features that are not only independent of the input transformation but also the features that encode the structure of geometric transformations. These complementary sets of features help generalize well to novel classes with only a few data samples. We achieve additional improvements by incorporating a novel self-supervised distillation objective. Our extensive experimentation shows that even without knowledge distillation our proposed method can outperform current state-of-the-art FSL methods on five popular benchmark datasets.