Collaborative Distillation for Ultra-Resolution Universal Style Transfer

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 1857 - 1866
• Main Authors: Wang, Huan, Li, Yijun, Wang, Yuehai, Hu, Haoji, Yang, Ming-Hsuan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2020
• Subjects: Collaboration; Decoding; Graphics processing units; Image coding; Image reconstruction; Knowledge engineering; Task analysis

Universal style transfer methods typically leverage rich representations from deep Convolutional Neural Network (CNN) models (e.g., VGG-19) pre-trained on large collections of images. Despite the effectiveness, its application is heavily constrained by the large model size to handle ultra-resolution...