Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, In-Jung | - |
dc.contributor.author | Choi, Changbeom | - |
dc.contributor.author | Lee, Sang-Heon | - |
dc.date.available | 2017-07-11T05:34:35Z | - |
dc.date.created | 2017-04-10 | - |
dc.date.issued | 2016-03 | - |
dc.identifier.issn | 1433-2833 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/2719 | - |
dc.description.abstract | The discrimination of similar patterns is important because they are the major sources of the classification error. This paper proposes a novel method to improve the discrimination ability of convolutional neural networks (CNNs) by hybrid learning. The proposed method embeds a collection of discriminators as well as a recognizer in a shared CNN. By visualizing contrastive class saliency, we show that learning with embedded discriminators leads the shared CNN to detect and catch the differences among similar classes. Also proposed is a hybrid learning algorithm that learns recognition and discrimination together. The proposed method learns recognition focusing on the differences among similar classes, and thereby improves the discrimination ability of the CNN. Unlike conventional discrimination methods, the proposed method does not require predefined sets of similar classes or additional step to integrate its result with that of the recognizer. In experiments on two handwritten Hangul databases SERI95a and PE92, the proposed method reduced classification error from 2.56 to 2.33, and from 4.04 to 3.66% respectively. These improvement lead to relative error reduction rates of 8.97% on SERI95a, and 9.42% on PE92. Our best results update the state-of-the-art performance which were 4.04% on SERI95a and 7.08% on PE92. © 2015, Springer-Verlag Berlin Heidelberg. | - |
dc.publisher | Springer Verlag | - |
dc.title | Improving discrimination ability of convolutional neural networks by hybrid learning | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/s10032-015-0256-9 | - |
dc.identifier.scopusid | 2-s2.0-84958763801 | - |
dc.identifier.bibliographicCitation | International Journal on Document Analysis and Recognition, v.19, no.1, pp.1 - 9 | - |
dc.subject.keywordAuthor | Hybrid learning | - |
dc.subject.keywordAuthor | Discrimination | - |
dc.subject.keywordAuthor | Character recognition | - |
dc.subject.keywordAuthor | Machine learning | - |
dc.subject.keywordAuthor | Pattern recognition | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordPlus | Artificial Intelligence | - |
dc.subject.keywordPlus | Character Recognition | - |
dc.subject.keywordPlus | Classification (of Information) | - |
dc.subject.keywordPlus | Classification Errors | - |
dc.subject.keywordPlus | Convolution | - |
dc.subject.keywordPlus | Convolutional Neural Network | - |
dc.subject.keywordPlus | Convolutional Neural Networks | - |
dc.subject.keywordPlus | Deep Learning | - |
dc.subject.keywordPlus | Discrimination | - |
dc.subject.keywordPlus | Discrimination Ability | - |
dc.subject.keywordPlus | Errors | - |
dc.subject.keywordPlus | Hybrid Learning | - |
dc.subject.keywordPlus | Hybrid Learning Algorithm | - |
dc.subject.keywordPlus | Learning Algorithms | - |
dc.subject.keywordPlus | Learning Systems | - |
dc.subject.keywordPlus | Machine Learning | - |
dc.subject.keywordPlus | Neural Networks | - |
dc.subject.keywordPlus | Pattern Recognition | - |
dc.subject.keywordPlus | State-of-the-Art Performance | - |
dc.citation.endPage | 9 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | International Journal on Document Analysis and Recognition | - |
dc.citation.volume | 19 | - |
There are no files associated with this item.