Few-Shot Learning via Saliency-Guided Hallucination of Samples

Citations Over TimeTop 1% of 2019 papers

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.

Related Papers

• → Source monitoring deficits in hallucinating compared to non-hallucinating patients with schizophrenia(2006)76 cited
• → Learning to Hallucinate Examples from Extrinsic and Intrinsic Supervision(2021)5 cited
• → Hallucinations in Children: A Follow‐up Study(1988)39 cited
• → Cooperative face hallucination using multiple references(2009)3 cited
• The hallucinating patient and nursing intervention.(1976)