深度神經網路近幾年在電腦視覺領域變得越來越熱門，最主要的原因在於其強大的特徵擷取能力。而在深度神經網路中，轉移學習對於避免過度擬合扮演了一個很重要的角色。在本篇論文裡，我們提出了一個基於分群的方法來整合完整標籤資料與弱標籤資料，並用這些資料來訓練一個卷積網路。透過轉移學習，這樣的卷積網路可以用來當作其他目標任務的預訓練模型。接著，我們設計了一個針對影像剖析問題的卷積網路架構來驗證我們的想法。初步的實驗結果顯示這樣的預訓練卷積網路可以有效地應用於轉移學習。

Deep neural networks have become more and more popular in computer vision because of their powerful ability to extract distinctive image features. In deep neural networks, transfer learning plays an important role to avoid overfitting. In this thesis, we present a clustering-based method to combine fully-labeled data with weakly-labeled data for convolutional networks. By transfer learning, these convolutional networks can be viewed as pre-trained models for another target task. Next, we design a framework of convolutional networks for scene parsing to demonstrate our idea. Preliminary experimental results show that it is helpful to use these pre-trained convolutional networks for transfer learning.

1 Introduction 7
2 Weakly-Supervised Convolutional Networks 9
2.1 Weaky-Labeled Data versus Fully-Labeled Data 9
2.2 Labeling by Clustering 9
2.3 Transferring Weights to Target Tasks 10
3 Convolutional Networks for Scene Parsing 12
3.1 Networks for Region-Level Problems 12
3.2 From Region-Level to Pixel-Level 13
4 Experiments 15
4.1 Dataset 15
4.2 Implementation Details 16
4.3 Results 16
4.3.1 Peformance of WSCNs 16
4.3.2 Evaluation for Superpixel Labeling 17
4.3.3 Results of Scene Parsing 17
5 Conclusion and Future Work 20

[1] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua,
and Sabine Susstrunk. SLIC superpixels compared to state-of-the-art superpixel
methods. IEEE Trans. Pattern Anal. Mach. Intell., 34(11):2274{2282, 2012.
[2] Yoshua Bengio. Deep learning of representations for unsupervised and transfer
learning. In Unsupervised and Transfer Learning - Workshop held at ICML 2011,
Bellevue, Washington, USA, July 2, 2011, pages 17{36, 2012.
[3] Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen
Lin. LIBLINEAR: A library for large linear classication. Journal of Machine
Learning Research, 9:1871{1874, 2008.
[4] Clement Farabet, Camille Couprie, Laurent Najman, and Yann LeCun. Learning
hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell.,
35(8):1915{1929, 2013.
[5] Ross B. Girshick, Je Donahue, Trevor Darrell, and Jitendra Malik. Rich feature
hierarchies for accurate object detection and semantic segmentation. In 2014
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014,
Columbus, OH, USA, June 23-28, 2014, pages 580{587, 2014.
[6] Junlin Hu, Jiwen Lu, and Yap-Peng Tan. Deep transfer metric learning. In The
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June
2015.
[7] Yangqing Jia, Evan Shelhamer, Je Donahue, Sergey Karayev, Jonathan Long,
Ross Girshick, Sergio Guadarrama, and Trevor Darrell. Cae: Convolutional
architecture for fast feature embedding. arXiv preprint arXiv:1408.5093, 2014.
[8] Alex Krizhevsky, Ilya Sutskever, and Georey E. Hinton. Imagenet classication
with deep convolutional neural networks. In Advances in Neural Information
Processing Systems 25: 26th Annual Conference on Neural Information Pro-
cessing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake
Tahoe, Nevada, United States., pages 1106{1114, 2012.
[9] Ce Liu, Jenny Yuen, and Antonio Torralba. Nonparametric scene parsing via
label transfer. IEEE Trans. Pattern Anal. Mach. Intell., 33(12):2368{2382, 2011.
[10] Maxime Oquab, Leon Bottou, Ivan Laptev, and Josef Sivic. Learning and transferring
mid-level image representations using convolutional neural networks. In
2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR
2014, Columbus, OH, USA, June 23-28, 2014, pages 1717{1724, 2014.
[11] Joseph Tighe and Svetlana Lazebnik. Superparsing - scalable nonparametric
image parsing with superpixels. International Journal of Computer Vision,
101(2):329{349, 2013.
[12] Jianxiong Xiao, James Hays, Krista A. Ehinger, Aude Oliva, and Antonio Torralba.
SUN database: Large-scale scene recognition from abbey to zoo. In The
Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition,
CVPR 2010, San Francisco, CA, USA, 13-18 June 2010, pages 3485{3492, 2010.
[13] Jason Yosinski, Je Clune, Yoshua Bengio, and Hod Lipson. How transferable are
features in deep neural networks? In Advances in Neural Information Processing
Systems 27: Annual Conference on Neural Information Processing Systems 2014,
December 8-13 2014, Montreal, Quebec, Canada, pages 3320{3328, 2014.