Skip to main content
Article
Exploring complementary strengths of invariant and equivariant representations for few-shot learning
arXiv
  • Mamshad Nayeem Rizve, Center for Research in Computer Vision
  • Salman Khan, Mohamed Bin Zayed University of Artificial Intelligence
  • Fahad Shahbaz Khan, Mohamed Bin Zayed University of Artificial Intelligence
  • Mubarak Shah, Center for Research in Computer Vision
Document Type
Article
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.

DOI
doi.org/10.48550/arXiv.2103.01315v2
Publication Date
4-19-2021
Comments

Preprint: arXiv

  • Archived with thanks to arXiv
  • Preprint License: CC BY-NC-SA 4.0
  • Uploaded 29 March 2022
Citation Information
M. N. Rizve, S. Khan, F. S. Khan and M. Shah, "Exploring complementary strengths of invariant and equivariant representations for few-shot learning," 2021, arXiv:2103.01315v2