Cited 1 time in
Cited 1 time in
Improving discrimination ability of convolutional neural networks by hybrid learning
- Improving discrimination ability of convolutional neural networks by hybrid learning
- Kim, IJ[Kim, In-Jung]; Choi, C[Choi, Changbeom]; Lee, SH[Lee, Sang-Heon]
- DGIST Authors
- Lee, SH[Lee, Sang-Heon]
- Issue Date
- International Journal on Document Analysis and Recognition, 19(1), 1-9
- Article Type
- Artificial Intelligence; Character Recognition; Classification (of Information); Classification Errors; Convolution; Convolutional Neural Network; Convolutional Neural Networks; Deep Learning; Discrimination; Discrimination Ability; Errors; Hybrid Learning; Hybrid Learning Algorithm; Learning Algorithms; Learning Systems; Machine Learning; Neural Networks; Pattern Recognition; State-of-the-Art Performance
- 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.
- Springer Verlag
- Related Researcher
There are no files associated with this item.
- Convergence Research Center for Future Automotive Technology1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.