跳到主要內容

臺灣博碩士論文加值系統

(44.220.255.141) 您好!臺灣時間:2024/11/15 01:10
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:朱皓安
研究生(外文):Hao-An Chu
論文名稱:使用基因規劃法整合卷積神經網路多層特徵用於影像分類
論文名稱(外文):A Genetic Programming Approach to Integrate Multilayer CNN Features for Image Classification
指導教授:朱威達
指導教授(外文):Wei-Ta Chu
口試委員:朱威達江振國葉梅珍邱志義
口試委員(外文):Wei-Ta ChuChen-Kuo ChiangMei-Chen YehChih-Yi Chiu
口試日期:2018-07-25
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2018
畢業學年度:106
語文別:英文
論文頁數:43
中文關鍵詞:基因規劃法卷積神經網路多層特徵影像分類
外文關鍵詞:genetic programmingconvolutional neural networksmultilayer featuresimage classification
相關次數:
  • 被引用被引用:0
  • 點閱點閱:423
  • 評分評分:
  • 下載下載:29
  • 收藏至我的研究室書目清單書目收藏:0
隨著卷積神經網路的廣泛使用,近年來有許多研究開始圍繞在如何有效利用卷積神經網路的多層特徵資訊。在許多領域中,整合從卷積神經網路提取的多層特徵已經被證實是有效的。在過去的研究,常見的特徵整合方式大多為串接以及Fisher vector編碼。
本論文提出使用基因規劃法(Genetic Programming)來整合多層特徵,藉由演化機制有系統地迭代並找出更好的多層特徵幫助影像分類。在實驗中我們在不同的影像資料集驗證使用基因規劃法自動找出的多層特徵整合方式有助於影像分類,並分析基因規劃法的特性以及演化的統計趨勢。本論文是少數使用演化式演算法(evolutionary algorithm)應用於多層特徵整合方式的研究。在實驗結果中表明了基因規劃法在自動找出特徵整合方式的潛力,並且啟發未來研究及改進的方向。

Fusing information extracted from multiple layers of a convolutional neural network has been proven effective in several domains. Common fusion techniques include feature concatenation and Fisher embedding.
In this thesis, we propose to fuse multilayer information from the perspective of genetic programming (GP). With the evolutionary strategy, we iteratively fuse multilayer information into a better representation in a systematic manner. In the evaluation, we verify the effectiveness of discovered GP-based representations on three image classification datasets, and discuss characteristics of the GP process. This study is one of the few works to fuse multilayer information based on an evolutionary strategy. The reported preliminary results not only demonstrate the potential of the GP fusion scheme, but also inspire future study in several aspects.
Contents 2
List of Figures 4
List of Tables 5
1 Introduction 6
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
1.2 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.3 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2 Related Works 10
2.1 Multilayer Features . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.2 Genetic Programming . . . . . . . . . . . . . . . . . . . . . . . . . 12
3 Proposed Method 14
3.1 Main Procedure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.2 Overview of Genetic Programming . . . . . . . . . . . . . . . . . . 15
3.2.1 Tree Structure Representation . . . . . . . . . . . . . . . . . 16
3.2.2 Phrase of GP . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.3 GP-based Combination . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.1 Terminal Set . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.2 Function Set . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.3.3 Fitness Function . . . . . . . . . . . . . . . . . . . . . . . . 23
3.3.4 Tree Height Limitation . . . . . . . . . . . . . . . . . . . . . 24
24 Experimental Results 25
4.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
4.2 Parameter Settings . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
4.3 Analysis and Discussion of Experiments . . . . . . . . . . . . . . . . 27
4.3.1 The Caltech-101 Dataset . . . . . . . . . . . . . . . . . . . . 27
4.3.2 The Caltech-256 Dataset . . . . . . . . . . . . . . . . . . . . 30
4.3.3 The Stanford-40 Dataset . . . . . . . . . . . . . . . . . . . . 31
4.3.4 Analysis on the Used Frequency of Terminal Set and Func-
tion Set . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
4.3.5 Comparion with Simple Concatenation . . . . . . . . . . . . 33
4.3.6 Time Consumption . . . . . . . . . . . . . . . . . . . . . . . 35
5 Conclusions and Future Work 37
Bibliography 39
[1] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of International Conference on Neural Information Processing Systems. 1097–1105.

[2] Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully Convolutional Networks for Semantic Segmentation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3] Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 6 (2017), 1137–1149.

[4] Matthew D. Zeiler and Rob Fergus. 2014. Visualizing and Understanding Convolutional Networks. In Proceedings of European Conference on Computer Vision.

[5] Erzhu Li, Junshi Xia, Peijun Du, Cong Lin, and Alim Samat. 2017. Integrating Multilayer Features of Convolutional Neural Networks for Remote Sensing Scene Classification. IEEE Transactions on Geoscience and Remote Sensing 55, 10 (2017), 5653–5665.

[6] Florent Perronnin, Jorge Sanchez, and Thomas Mensink. 2010. Improving the Fisher Kernel for Large-Scale Image Classification. In Proceedings of European Conference on Computer Vision.

[7] Xiaodong Yang, Pavlo Molchanov, and Jan Kautz. 2016. Multilayer and Multimodal Fusion of Deep Neural Networks for Classification. In Proceedings of ACM Multimedia Conference. 978–987.

[8] John R. Koza. 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press.

[9] John H. Holland. 1992. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence. MIT Press.

[10] Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional Architecture for Fast Feature Embedding. In Proceedings of ACM International Conference on Multimedia. 675–678.

[11] Ken Chatfield, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2014. Return of the Devil in the Details: Delving Deep into Convolutional Networks. In Proceedings of British Machine Vision Conference.

[12] Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of International Conference on Learning Representation.

[13] Yukhe Lavinia, Holly H. Vo, and Abhishek Verma. 2016. Fusion Based Deep CNN for Improved Large-Scale Image Action Recognition. In Proceedings of IEEE International Symposium on Multimedia. 609-614.

[14] Songfan Yang and Deva Ramanan. 2015. Multi-scale Recognition with DAG-CNNs. In Proceedings of IEEE International Conference on Computer Vision.

[15] Bharath Hariharan, Pablo Arbelaez, Ross Girshick, and Jitendra Malik. 2015. Hypercolumns for Object Segmentation and Fine-grained Localization. In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition.

[16] Alexey Dosovitskiy, Philipp Fischer, Eddy Ilg, Philip Hausser, Caner Hazirbas, Vladimir Golkov, Patrick van der Smagt, Daniel Cremers, and Thomas Brox. 2015. FlowNet: Learning Optical Flow with Convolutional Networks. In Proceedings of IEEE International Conference on Computer Vision.

[17] Ling Shao, Li Liu, and Xuelong Li. 2014. Feature Learning for Image Classification Via Multiobjective Genetic Programming. IEEE Transactions on Neural Networks and Learning Systems 25, 7 (2014), 1359–1371.

[18] Yuyu Liang, Mengjie Zhang, and Will N. Browne. 2016. Figure-ground Image Segmentation Using Genetic Programming and Feature Selection. In Proceedings of IEEE Congress on Evolutionary Computation.

[19] Harith Al-Sahaf, Ausama Al-Sahaf, Bing Xue, Mark Johnston, and Mengjie Zhang. 2017. Automatically Evolving Rotation-Invariant Texture Image Descriptors by Genetic Programming. IEEE Transactions on Evolutionary Computation 21, 1 (2017), 83–101.

[20] Masanori Suganuma, Shinichi Shirakawa, and Tomoharu Nagao. 2017. A Genetic Programming Approach to Designing Convolutional Neural Network Architectures. In Proceedings of the Genetic and Evolutionary Computation Conference. 497–504.

[21] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich. 2015. Going Deeper with Convolutions. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition.

[22] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition. 770-778.

[23] Li Fei-Fei, Rob Fergus, and Pietro Perona. 2004. Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories. In Proceedings of CVPR Workshop of Generative Model Based Vision.

[24] Gregory Griffin, Alex Holub, and Pietro Perona. 2007. Caltech-256 Object Category Dataset. Technical Report. California Institute of Technology.

[25] Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas Guibas, and Li Fei-Fei. 2011. Human Action Recognition by Learning Bases of Action Attributes and Parts. In Proceedings of IEEE International Conference on Computer Vision.

[26] Navneet Dadal and Bill Triggs. 2005. Histograms of Oriented Gradients for Human Detection. In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. 886–893.

[27] David Lowe. 2004. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 2 (2004), 91–110.

[28] Timo Ahoene, Abdenour Hadid, and Matti Pietikainen. 2004. Face Recognition with Local Binary Patterns. In Proceedings of European Conference on Computer Vision. 469–481.

[29] David Martin, Charless Fowlkes, Doron Tal, and Jitendra Malik. 2001. A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition. 416–423.

[30] Jianxin Wu and Jim Rehg. 2011. CENTRIST: A Visual Descriptor for Scene Categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 8 (2011), 1489–1501.

[31] Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top