CIOMP OpenIR
Unimodal regularized neuron stick-breaking for ordinal classification
X. F. Liu; F. F. Fan; L. S. Kong; Z. H. Diao; W. Q. Xie; J. Lu and J. N. You
2020
Source PublicationNeurocomputing
ISSN0925-2312
Volume388Pages:34-44
AbstractThis paper targets for the ordinal regression/classification, which objective is to learn a rule to predict labels from a discrete but ordered set. For instance, the classification for medical diagnosis usually involves inherently ordered labels corresponding to the level of health risk. Previous multi-task classifiers on ordinal data often use several binary classification branches to compute a series of cumulative probabilities. However, these cumulative probabilities are not guaranteed to be monotonically decreasing. It also introduces a large number of hyper-parameters to be fine-tuned manually. This paper aims to eliminate or at least largely reduce the effects of those problems. We propose a simple yet efficient way to rephrase the output layer of the conventional deep neural network. Besides, in order to alleviate the effects of label noise in ordinal datasets, we propose a unimodal label regularization strategy. It also explicitly encourages the class predictions to distribute on nearby classes of ground truth. We show that our methods lead to the state-of-the-art accuracy on the medical diagnose task (e.g., Diabetic Retinopathy and Ultrasound Breast dataset) as well as the face age prediction (e.g., Adience face and MORPH Album II) with very little additional cost. (C) 2020 Elsevier B.V. All rights reserved.
DOI10.1016/j.neucom.2020.01.025
URL查看原文
Indexed BySCI
Language英语
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ciomp.ac.cn/handle/181722/64994
Collection中国科学院长春光学精密机械与物理研究所
Recommended Citation
GB/T 7714
X. F. Liu,F. F. Fan,L. S. Kong,et al. Unimodal regularized neuron stick-breaking for ordinal classification[J]. Neurocomputing,2020,388:34-44.
APA X. F. Liu,F. F. Fan,L. S. Kong,Z. H. Diao,W. Q. Xie,&J. Lu and J. N. You.(2020).Unimodal regularized neuron stick-breaking for ordinal classification.Neurocomputing,388,34-44.
MLA X. F. Liu,et al."Unimodal regularized neuron stick-breaking for ordinal classification".Neurocomputing 388(2020):34-44.
Files in This Item: Download All
File Name/Size DocType Version Access License
Unimodal regularized(2352KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[X. F. Liu]'s Articles
[F. F. Fan]'s Articles
[L. S. Kong]'s Articles
Baidu academic
Similar articles in Baidu academic
[X. F. Liu]'s Articles
[F. F. Fan]'s Articles
[L. S. Kong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[X. F. Liu]'s Articles
[F. F. Fan]'s Articles
[L. S. Kong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Unimodal regularized neuron stick-breaking for.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.