Training convolutional autoencoders with metric learning

Yosuke Onitsuka, Wataru Oyama, Seiichi Uchida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a new Training method that enables an autoencoder to extract more useful features for retrieval or classification tasks with limited-size datasets. Some targets in document analysis and recognition (DAR) including signature verification, historical document analysis, and scene text recognition, involve a common problem in which the size of the dataset available for training is small against the intra-class variety of the target appearance. Recently, several approaches, such as variational autoencoders and deep metric learning, have been proposed to obtain a feature representation that is suitable for the tasks. However, these methods sometimes cause an overfitting problem in which the accuracy of the test data is relatively low, while the performance for the training dataset is quite high. Our proposed method obtains feature representations for such tasks in DAR using convolutional autoencoders with metric learning. The accuracy is evaluated on an image-based retrieval of ancient Japanese signatures.

Original languageEnglish
Title of host publicationProceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
PublisherIEEE Computer Society
Pages86-91
Number of pages6
ISBN (Electronic)9781728128610
DOIs
Publication statusPublished - Sep 2019
Event15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 - Sydney, Australia
Duration: Sep 20 2019Sep 25 2019

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)1520-5363

Conference

Conference15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
CountryAustralia
CitySydney
Period9/20/199/25/19

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Onitsuka, Y., Oyama, W., & Uchida, S. (2019). Training convolutional autoencoders with metric learning. In Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 (pp. 86-91). [8977957] (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). IEEE Computer Society. https://doi.org/10.1109/ICDAR.2019.00023