Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
arXiv:1904.08482
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.
Accepted to CVPR 2019
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Auto-Encoding Variational Bayes
- Prototypical Networks for Few-shot Learning
- Matching Networks for One Shot Learning
- A Simple Neural Attentive Meta-Learner
- Generalized Denoising Auto-Encoders as Generative Models
- Understanding Infographics through Textual and Visual Tag Prediction
- Co-domain Embedding using Deep Quadruplet Networks for Unseen Traffic Sign Recognition