Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval 論文筆記
0 摘要 本文基於深度卷積神經網絡學習的特徵，提出了一種新的文檔圖像分類和檢索的技術。 在物體分類和場景分析中，深度神經網絡能夠從像素級別的輸入中學習到分層的抽象特徵，並簡潔地表達出來。目前在文檔分析領域探索的一些工作表明，深度學習的特徵表達策略優於傳統流行的手工提取特徵。實驗還表明： （i）從CNN中提取的特徵對於壓縮具有魯棒性； （ii）在非文檔圖像上訓練的CNN可以很好地遷移到文檔分
相關文章
- 1. 論文筆記：DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and......
- 2. 論文筆記：Very Deep Convolutional Networks for Large-Scale Image Recognition
- 3. 論文筆記：An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- 4. Bag of Tricks for Image Classification with Convolutional Neural Networks論文筆記
- 5. 《Bag of Tricks for Image Classification with Convolutional Neural Networks》論文閱讀筆記
- 6. 論文閱讀（6）：Deep Clustering and Block Hashing Network for Face Image Retrieval
- 7. FitNets: Hints for thin deep nets論文筆記
- 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》論文筆記
- 更多相關文章...
- • XSLT document() 函數 - XSLT 教程
- • XML DOM - Document 對象 - XML DOM 教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • RxJava操作符（七）Conditional and Boolean
相關標籤/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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 論文筆記：DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,and......
- 2. 論文筆記：Very Deep Convolutional Networks for Large-Scale Image Recognition
- 3. 論文筆記：An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- 4. Bag of Tricks for Image Classification with Convolutional Neural Networks論文筆記
- 5. 《Bag of Tricks for Image Classification with Convolutional Neural Networks》論文閱讀筆記
- 6. 論文閱讀（6）：Deep Clustering and Block Hashing Network for Face Image Retrieval
- 7. FitNets: Hints for thin deep nets論文筆記
- 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》論文筆記