Demystifying Neural Style Transfer
Demystifying Neural Style Transfer
Yanghao Li, Naiyan Wang, Jiaying Liu, Xiaodi Hou
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 2230-2236.
https://doi.org/10.24963/ijcai.2017/310
Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains unclear. In this paper, we propose a novel interpretation of neural style transfer by treating it as a domain adaptation problem. Specifically, we theoretically show that matching the Gram matrices of feature maps is equivalent to minimize the Maximum Mean Discrepancy (MMD) with the second order polynomial kernel. Thus, we argue that the essence of neural style transfer is to match the feature distributions between the style images and the generated images. To further support our standpoint, we experiment with several other distribution alignment methods, and achieve appealing results. We believe this novel interpretation connects these two important research fields, and could enlighten future researches.
Keywords:
Machine Learning: Transfer, Adaptation, Multi-task Learning
Multidisciplinary Topics and Applications: Art and Music
Machine Learning: Deep Learning