DropSample: A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten Chinese character recognition
详细信息 查看全文
- 作者：Weixin YangaAuthor Vitae ; Lianwen Jina ; lianwen.jin@gmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Dacheng TaobAuthor Vitae ; Zecheng XieaAuthor Vitae ; Ziyong FengaAuthor Vitae
- 关键词：Convolutional neural network ; Deep learning ; Handwritten character recognition ; Domain-specific knowledge
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：October 2016
- 年：2016
- 卷：58
- 期：Complete
- 页码：190-203
- 全文大小：2102 K
文摘
- •
We propose a novel and efficient training method for CNN on large-scale data.
- •
DropSample adaptively selects training samples and is robust to noisy data.
- •
The incorporation of domain-specific knowledge enhances the performance of CNN.
- •
New state-of-the-art results are reported on 3 online handwritten Chinese character datasets.