Method for learning cross-domain relations based on generative adversarial networks
作者： Kim Ji Won , Cha Moon Su , Kim Taek Soo
DOI:
关键词: Translation (geometry) 、 Domain (software engineering) 、 Adversarial system 、 Generative grammar 、 Sample (graphics) 、 Loop (topology) 、 Algorithm 、 Computer science
摘要: A generative adversarial networks-based or GAN-based method for learning cross-domain relations is disclosed. provided architecture includes two coupled GANs: a first GAN translation of images from domain to B, and second B A. loop formed by the causes sample be reconstructed into an original after being translated target domain. Therefore, loss functions representing reconstruction losses may used train models.
lens.org 参考文章(26)
Tinghui Zhou, Philipp Krahenbuhl, Mathieu Aubry, Qixing Huang, Alexei A. Efros, Learning Dense Correspondence via 3D-Guided Cycle Consistency computer vision and pattern recognition. pp. 117- 126 ,(2016) , 10.1109/CVPR.2016.20
Paolo Russo, Fabio M. Carlucci, Tatiana Tommasi, Barbara Caputo, From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8099- 8108 ,(2018) , 10.1109/CVPR.2018.00845
Oncel Tuzel, Ming-Yu Liu, Method and system for generating multimodal digital images ,(2016)
Xiaodan Liang, Luona Yang, Eric P. Xing, Unsupervised Real-to-Virtual Domain Unification for End-to-End Highway Driving ,(2018)
Boris Chidlovskii, Stéphane Clinchant, Gabriela Csurka, System and method for domain adaptation using marginalized stacked denoising autoencoders with domain prediction regularization ,(2016)
Kanebako Yusuke, Tanaka Takuya, METHOD AND SYSTEM OF GENERATIVE MODEL LEARNING, AND PROGRAM PRODUCT ,(2018)
Vlachou-Konchylaki Martha, Huang Vincent, Ley Tobias, Hu Wenfeng, PRE-TRAINING SYSTEM FOR SELF-LEARNING AGENT IN VIRTUALIZED ENVIRONMENT ,(2020)
Tolpin David, Myara Benjamin Hillel, Fraud prediction based on partial usage data ,(2018)
Choi Wongun, Schulter Samuel, Sohn Kihyuk, Chandraker Manmohan, Cyclic generative adversarial network for unsupervised cross-domain image generation ,(2018)
Ming-Yu Liu, Thomas Michael Breuel, Jan Kautz, None, SYSTEMS AND METHODS FOR IMAGE-TO-IMAGE TRANSLATION USING VARIATIONAL AUTOENCODERS ,(2018)