Adversarial Feature Hallucination Networks for Few-Shot Learning

Abstract

The recent flourish of deep learning in various tasks is largely accredited to the rich and accessible labeled data. Nonetheless, massive supervision remains a luxury for many real applications, boosting great interest in label-scarce techniques such as few-shot learning (FSL), which aims to learn concept of new classes with a few labeled samples. A natural approach to FSL is data augmentation and many recent works have proved the feasibility by proposing various data synthesis models. However, these models fail to well secure the discriminability and diversity of the synthesized data and thus often produce undesirable results. In this paper, we propose Adversarial Feature Hallucination Networks (AFHN) which is based on conditional Wasserstein Generative Adversarial networks (cWGAN) and hallucinates diverse and discriminative features conditioned on the few labeled samples. Two novel regularizers, i.e., the classification regularizer and the anti-collapse regularizer, are incorporated into AFHN to encourage discriminability and diversity of the synthesized features, respectively. Ablation study verifies the effectiveness of the proposed cWGAN based feature hallucination framework and the proposed regularizers. Comparative results on three common benchmark datasets substantiate the superiority of AFHN to existing data augmentation based FSL approaches and other state-of-the-art ones.

arXiv commentCorrect some typos

References in corpus (13)

• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Few-Shot Learning with Graph Neural Networks
• Delta-encoder: an effective sample synthesis method for few-shot object recognition
• Few-Shot Learning with Metric-Agnostic Conditional Embeddings
• Deep Meta-Learning: Learning to Learn in the Concept Space
• Low-Shot Learning from Imaginary Data
• Memory Matching Networks for One-Shot Image Recognition
• Edge-labeling Graph Neural Network for Few-shot Learning
• Image Deformation Meta-Networks for One-Shot Learning

Cited by in corpus (4)

• Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
• Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
• Unsupervised data augmentation for object detection
• Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis