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

by   Mamshad Nayeem Rizve, et al.

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.


Self-supervised Knowledge Distillation for Few-shot Learning

Real-world contains an overwhelmingly large number of object classes, le...

FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers

One of the most significant challenges facing a few-shot learning task i...

ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning

Self-supervised learning (SSL) techniques have recently been integrated ...

Supervised Masked Knowledge Distillation for Few-Shot Transformers

Vision Transformers (ViTs) emerge to achieve impressive performance on m...

Diversity with Cooperation: Ensemble Methods for Few-Shot Classification

Few-shot classification consists of learning a predictive model that is ...

Please sign up or login with your details

Forgot password? Click here to reset