papers AI Learner
The Github is limit! Click to go to the new site.

Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images

2019-04-17
Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon

Abstract

In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot classification with prototypical images as a single training example for each novel class. We take an approach to learn a generalizable embedding space for novel tasks. We propose a new approach called variational prototyping-encoder (VPE) that learns the image translation task from real-world input images to their corresponding prototypical images as a meta-task. As a result, VPE learns image similarity as well as prototypical concepts which differs from widely used metric learning based approaches. Our experiments with diverse datasets demonstrate that the proposed VPE performs favorably against competing metric learning based one-shot methods. Also, our qualitative analyses show that our meta-task induces an effective embedding space suitable for unseen data representation.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.08482

PDF

http://arxiv.org/pdf/1904.08482


Similar Posts

Comments