arrow
返回

Unsupervised Exemplar-Based Learning for Improved Document Image Classification

delete2019-01-01
delete7
delete
OA
AI
S
Sherif Abuelwafa *
M
Marco Pedersoli
M
Mohamed Cheriet
DOI:10.1109/ACCESS.2019.2940884delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Many recent state-of-the-art approaches for document image classification are based on supervised feature learning that requires a large amount of labeled training data. In real-world problem of document image classification, the available amount of labeled data is limited and scarce while a large amount of unlabeled data is often available at almost no cost. In this paper, we present an approach for learning visual features for document analysis in an unsupervised way, which improves the document image classification performance without increasing the amount of annotated data. The proposed approach trains a neural network model on an auxiliary task in which every training example is associated with a different label (exemplar) and expanded to multiple images through a data augmentation technique. Thus, the learned model, which is trained in an unsupervised way, is used to boost the document classification performance. In fact, this learned model has proved to be consistently efficient in two different settings: i) as an unsupervised feature extractor to represent document images for an unsupervised classification task (i.e., clustering); and ii) in the parameters initialization of a supervised classification task trained with a small amount of annotated data. We perform experiments on the Tobacco-3482 dataset and demonstrate the capability of our approach to improve i) the unsupervised classification accuracy up to 2.4%; and ii) the supervised classification accuracy by 1.5% without any extra data or by 5% when using 3000 additional not annotated samples.
Keyword:
Document image classification
document analysis
document image representation
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
36.3W

机构

U
university of quebec
学者数:
206
论文数: 103
被引数: 1.2W
引用论文

引用论文

ImageNet Large Scale Visual Recognition ChallengeImageNet大规模视觉识别挑战
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
err分享
err收藏
Air Current Applied to the Face Improves Exercise Performance in Patients with COPD
errLung
IF0
err2015-08-09
err0
errOAAI
errNathaniel Marchetti; Matthew R. Lammi; John M. Travaline; David Ciccolella; Brian Civic; Gerard J. Criner
err分享
err收藏
err分享
err收藏
Learning Cooperative Personalized Policies from Gaze Data
err2019-10-17
err0
PREAI
errChristoph Gebhardt; Brian Hecox; Bas van Opheusden; Daniel Wigdor; James Hillis; Otmar Hilliges; Hrvoje Benko
err分享
err收藏
Artefactual Nanoparticle Activation of the Inflammasome Platform: in Vitro Evidence with a Nano-Formed Calcium Phosphate
err2014-07-03
err0
errOAAI
errLaetitia Pele; Carolin T Haas; Rachel Hewitt; Nuno Faria; Andy Brown; Jonathan Powell
err分享
err收藏
学者 查看更多内容