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

04/17/2019
by   Junsik Kim, et al.
0

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.

READ FULL TEXT

page 1

page 6

page 7

page 8

page 13

page 14

page 15

research
09/09/2020

Proxy Network for Few Shot Learning

The use of a few examples for each class to train a predictive model tha...
research
11/22/2022

Adaptive Prototypical Networks

Prototypical network for Few shot learning tries to learn an embedding f...
research
05/19/2018

Diverse Few-Shot Text Classification with Multiple Metrics

We study few-shot learning in natural language domains. Compared to many...
research
10/17/2020

Directed Variational Cross-encoder Network for Few-shot Multi-image Co-segmentation

In this paper, we propose a novel framework for multi-image co-segmentat...
research
06/08/2022

Metric Based Few-Shot Graph Classification

Many modern deep-learning techniques do not work without enormous datase...
research
11/23/2022

InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images

Common Deep Metric Learning (DML) datasets specify only one notion of si...
research
04/03/2023

OTS: A One-shot Learning Approach for Text Spotting in Historical Manuscripts

Historical manuscript processing poses challenges like limited annotated...

Please sign up or login with your details

Forgot password? Click here to reset