SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.13193 · 2020

Adversarial Feature Hallucination Networks for Few-Shot Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.13193")
get_code_for_paper("2003.13193")
have("2003.13193")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.13193.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.13193.svg)](https://syntology.ai/paper/2003.13193)

Connect an agent — have() is free.