2017/01/04 by Yanghao Li, Li, Yanghao, Naiyan Wang +5 · 1 voice · 15 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #cs.CV #cs.LG #cs.NE
paper · pdf · doi:10.48550/arxiv.1701.01036
openalex publication_date 2017/01/04 · arxiv published 2017/01/04 · arxiv updated 2017/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.