單領域監督之跨領域深度解離特徵學習

Learning Cross-Domain Feature Disentanglement with Supervision from A Single Domain

劉彥成(Yen-Cheng Liu)

指導教授 ： 王勝德

共同指導教授 ： 王鈺強(Yu-Chiang Frank Wang)

國立臺灣大學/電機資訊學院/電機工程學研究所/碩士(2017年)

https://doi.org/10.6342/NTU201702026

摘要

深度生成模型於電腦視覺與機器學習領域中,近期有顯著發展與影響。特徵解離主要在不可分析之潛在向量中分離出具有語義之個別特徵,傳統方法多為監督學習框架,少數非監督學習框架則無法確保解離語義之穩定性。本篇論文中,我們將提出深度生成類神經網路架構,在單邊領域監督之下,達成跨領域解離語義特徵學習,同時在本文中,我們應用非監督領域適應之概念,學習共同特徵解離與適應。藉由生成對抗學習架構,本文將出新式具特徵解離能力之深度學習架構,此架構將同時訓練於跨領域資料,學習出具有共同語義之分離特徵,進而在生成模型框架之下,完成單領域監督之跨領域深度解離特徵學習。本文實驗中,我們利用此深度生成架構,將原始輸入影像於潛在空間空改變屬性後,生成對應屬性之跨領域影像。同時也將呈現單邊監督情況之下,利用此深度網路架構,完成雙邊領域個別之影像分類,解決非監督領域適應影像分類問題。

關鍵字

解離特徵 ； 領域適應 ； 對抗生成學習網路 ； 多樣式自動編碼器

並列摘要

The recent progress and development of deep generative models have led to remarkable improvements in research topics in computer vision and machine learning. In this article, the task of cross-domain feature disentanglement is addressed. This thesis advances the idea of unsupervised domain adaptation and propose to perform joint feature disentanglement and adaptation. Based on generative adversarial networks, a novel deep learning architecture with disentanglement ability is presented, which observes cross-domain image data and derives latent features with the underlying factors(e.g., attributes). As a result, our generative model is able to address cross-domain feature disentanglement with only the (attribute) supervision from the source-domain data (not the target-domain ones). In the experiments, the model is applied for generating and classifying images with particular attributes, and show that satisfactory results can be produced.

並列關鍵字

Feature Disentanglement ； Domain Adaptation ； Generative Adversarial Networks ； Variational Autoencoder

參考文獻

[4] Y. Güçlütürk, U. Güçlü, R. van Lier, and M. AJ van Gerven, “Convolutional sketch inversion,” in Proceedings of the European Conference on Computer Vision (ECCV), 2016.

[9] D. P. Kingma, S. Mohamed, D. Jimenez Rezende, and Max Welling,” Semi-supervised learning with deep generative models,” in Advances in Neural Information Processing Systems (NIPS), 2014.

[10] T. D. Kulkarni, W. F. Whitney, P. Kohli, and J. Tenenbaum, “Deep convolutional inverse graphics network,” in Advances in Neural Information Processing Systems (NIPS), 2015.

[11] M.-Y. Liu and O. Tuzel, “Coupled generative adversarial networks,” in Advances in Neural Information Processing Systems (NIPS), 2016.

[17] V. M. Patel, R. Gopalan, R. Li, and R. Chellappa, “Visual domain adaptation: A survey of recent advances,” IEEE Signal Processing Magazine, 32(3):53– 69, 2015.