Adversarial Feature Hallucination Networks for Few-Shot Learning

TL;DR

This paper introduces AFHN, a novel adversarial network that hallucinates diverse, discriminative features for few-shot learning, significantly improving data augmentation quality and classification performance on benchmark datasets.

Contribution

The paper proposes a new cWGAN-based framework with regularizers to enhance feature diversity and discriminability in few-shot learning.

Findings

AFHN outperforms existing data augmentation methods in FSL.

Regularizers improve the quality of synthesized features.

Ablation studies confirm the effectiveness of the proposed components.

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.