Few-Shot Learning with Geometric Constraints

Abstract

In this article, we consider the problem of few-shot learning for classification. We assume a network trained for base categories with a large number of training examples, and we aim to add novel categories to it that have only a few, e.g., one or five, training examples. This is a challenging scenario because: 1) high performance is required in both the base and novel categories; and 2) training the network for the new categories with a few training examples can contaminate the feature space trained well for the base categories. To address these challenges, we propose two geometric constraints to fine-tune the network with a few training examples. The first constraint enables features of the novel categories to cluster near the category weights, and the second maintains the weights of the novel categories far from the weights of the base categories. By applying the proposed constraints, we extract discriminative features for the novel categories while preserving the feature space learned for the base categories. Using public data sets for few-shot learning that are subsets of ImageNet, we demonstrate that the proposed method outperforms prevalent methods by a large margin.

arXiv commentAccepted for publication in IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Overcoming catastrophic forgetting in neural networks
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Fully Convolutional Networks for Semantic Segmentation
• A Simple Neural Attentive Meta-Learner
• NormFace: L2 Hypersphere Embedding for Face Verification
• Large Margin Few-Shot Learning

Cited by in corpus (5)

• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classification
• Gradual Relation Network: Decoding Intuitive Upper Extremity Movement Imaginations Based on Few-Shot EEG Learning
• High-order structure preserving graph neural network for few-shot learning
• An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling