Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval 论文笔记
0 摘要 本文基于深度卷积神经网络学习的特征，提出了一种新的文档图像分类和检索的技术。 在物体分类和场景分析中，深度神经网络能够从像素级别的输入中学习到分层的抽象特征，并简洁地表达出来。目前在文档分析领域探索的一些工作表明，深度学习的特征表达策略优于传统流行的手工提取特征。实验还表明： （i）从CNN中提取的特征对于压缩具有鲁棒性； （ii）在非文档图像上训练的CNN可以很好地迁移到文档分
相关文章
- 1. 论文笔记：DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and......
- 2. 论文笔记：Very Deep Convolutional Networks for Large-Scale Image Recognition
- 3. 论文笔记：An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- 4. Bag of Tricks for Image Classification with Convolutional Neural Networks论文笔记
- 5. 《Bag of Tricks for Image Classification with Convolutional Neural Networks》论文阅读笔记
- 6. 论文阅读（6）：Deep Clustering and Block Hashing Network for Face Image Retrieval
- 7. FitNets: Hints for thin deep nets论文笔记
- 8. Deep Convolutional Nets for Semantic Image Segmentation with Deep Gaussian CRFs
- 9. Deep Learning for Information Retrieval
- 10. 《DeepLab v1：semantic image segmentation with deep convolutional nets and fully connected CRFs》论文笔记
- 更多相关文章...
- • XSLT document() 函数 - XSLT 教程
- • XML DOM - Document 对象 - XML DOM 教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • RxJava操作符（七）Conditional and Boolean
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文笔记：DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and......
- 2. 论文笔记：Very Deep Convolutional Networks for Large-Scale Image Recognition
- 3. 论文笔记：An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- 4. Bag of Tricks for Image Classification with Convolutional Neural Networks论文笔记
- 5. 《Bag of Tricks for Image Classification with Convolutional Neural Networks》论文阅读笔记
- 6. 论文阅读（6）：Deep Clustering and Block Hashing Network for Face Image Retrieval
- 7. FitNets: Hints for thin deep nets论文笔记
- 8. Deep Convolutional Nets for Semantic Image Segmentation with Deep Gaussian CRFs
- 9. Deep Learning for Information Retrieval
- 10. 《DeepLab v1：semantic image segmentation with deep convolutional nets and fully connected CRFs》论文笔记