Please use this identifier to cite or link to this item:
|Title:||A framework of extracting multi-scale features using multiple convolutional neural networks||Authors:||Peng K.-C.
|Keywords:||Convolutional neural networks
|Issue Date:||2015||Publisher:||IEEE Computer Society||Citation:||Peng K.-C., Chen T. (2015). A framework of extracting multi-scale features using multiple convolutional neural networks. Proceedings - IEEE International Conference on Multimedia and Expo 2015-August : 7177449. ScholarBank@NUS Repository. https://doi.org/10.1109/ICME.2015.7177449||Abstract:||Most works related to convolutional neural networks (CNN) use the traditional CNN framework which extracts features in only one scale. We propose multi-scale convolutional neural networks (MSCNN) which can not only extract multi-scale features but also solve the issues of the previous methods which use CNN to extract multi-scale features. With the assumption of label-inheritable (LI) property, we also propose a method to generate exponentially more training examples for MSCNN from the given training set. Our experimental results show that MSCNN outperforms both the state-of-the-art methods and the traditional CNN framework on artist, artistic style, and architectural style classification, supporting that MSCNN outperforms the traditional CNN framework on the tasks which at least partially satisfy LI property.||Source Title:||Proceedings - IEEE International Conference on Multimedia and Expo||URI:||http://scholarbank.nus.edu.sg/handle/10635/146079||ISBN:||9781479970827||ISSN:||19457871||DOI:||10.1109/ICME.2015.7177449|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Oct 16, 2021
checked on Oct 14, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.