Large Margin Few-Shot Learning

Abstract

The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework to learn a more discriminative metric space by augmenting the classification loss function with a large margin distance loss function for training. Extensive experiments on two state-of-the-art few-shot learning methods, graph neural networks and prototypical networks, show that our method can improve the performance of existing models substantially with very little computational overhead, demonstrating the effectiveness of the large margin principle and the potential of our method.

arXiv comment17 pages, 5 figures, 7 tables

References in corpus (9)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Matching Networks for One Shot Learning
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Few-Shot Learning with Graph Neural Networks
• Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
• Generative Adversarial Residual Pairwise Networks for One Shot Learning
• Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

Cited by in corpus (7)

• Few-Shot Learning with Geometric Constraints
• One-Shot Instance Segmentation
• Comparison Network for One-Shot Conditional Object Detection
• Variational Metric Scaling for Metric-Based Meta-Learning
• Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification
• Contrastive Weight Regularization for Large Minibatch SGD
• Recent Advances in Large Margin Learning