Few-Shot Learning with Global Class Representations

Abstract

In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples. In each training episode, an episodic class mean computed from a support set is registered with the global representation via a registration module. This produces a registered global class representation for computing the classification loss using a query set. Though following a similar episodic training pipeline as existing meta learning based approaches, our method differs significantly in that novel class training samples are involved in the training from the beginning. To compensate for the lack of novel class training samples, an effective sample synthesis strategy is developed to avoid overfitting. Importantly, by joint base-novel class training, our approach can be easily extended to a more practical yet challenging FSL setting, i.e., generalized FSL, where the label space of test data is extended to both base and novel classes. Extensive experiments show that our approach is effective for both of the two FSL settings.

Accepted by ICCV2019

References in corpus (4)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Prototypical Networks for Few-shot Learning
• One-shot Learning with Memory-Augmented Neural Networks
• One-Shot Generalization in Deep Generative Models

Cited by in corpus (13)

• Robust High-dimensional Memory-augmented Neural Networks
• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?
• Self-supervised Knowledge Distillation for Few-shot Learning
• Restoring Negative Information in Few-Shot Object Detection
• DPGN: Distribution Propagation Graph Network for Few-shot Learning
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• Relational Generalized Few-Shot Learning
• Region Comparison Network for Interpretable Few-shot Image Classification
• Boosting Few-Shot Learning With Adaptive Margin Loss
• Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
• Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
• Enabling the Network to Surf the Internet
• Class Interference Regularization