Few-Shot Learning via Saliency-guided Hallucination of Samples

TL;DR

This paper introduces a novel, cost-effective few-shot learning method that uses saliency maps to hallucinate new data points directly in feature space, improving learning with limited samples.

Contribution

It presents the first use of saliency maps for data hallucination in few-shot learning, bypassing the need for complex generative models like GANs.

Findings

Achieves state-of-the-art results on public datasets.

Demonstrates effectiveness of saliency-guided hallucination.

Reduces reliance on large annotated datasets for data generation.

Abstract

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) generating or hallucinating additional data from the limited existing samples. In this paper, we follow the latter direction and present a novel data hallucination model. Currently, most datapoint generators contain a specialized network (i.e., GAN) tasked with hallucinating new datapoints, thus requiring large numbers of annotated data for their training in the first place. In this paper, we propose a novel less-costly hallucination method for few-shot learning which utilizes saliency maps. To this end, we employ a saliency network to obtain the foregrounds and backgrounds of available image samples and feed the resulting maps into a two-stream network to hallucinate datapoints directly in the feature space from viable foreground-background combinations. To the best of our knowledge, we are the first to leverage saliency maps for such a task and we demonstrate their usefulness in hallucinating additional datapoints for few-shot learning. Our proposed network achieves the state of the art on publicly available datasets.