arXiv Analytics

Sign in

arXiv:1905.12261 [cs.CV]AbstractReferencesReviewsResources

KG-GAN: Knowledge-Guided Generative Adversarial Networks

Che-Han Chang, Chun-Hsien Yu, Szu-Ying Chen, Edward Y. Chang

Published 2019-05-29Version 1

Generative adversarial networks (GANs) learn to mimic training data that represents the underlying true data distribution. However, GANs suffer when the training data lacks quantity or diversity and therefore cannot represent the underlying distribution well. To improve the performance of GANs trained on under-represented training data distributions, this paper proposes KG-GAN to fuse domain knowledge with the GAN framework. KG-GAN trains two generators; one learns from data while the other learns from knowledge. To achieve KG-GAN, domain knowledge is formulated as a constraint function to guide the learning of the second generator. We validate our framework on two tasks: fine-grained image generation and hair recoloring. Experimental results demonstrate the effectiveness of KG-GAN.

Comments: Submitted to NeurIPS 2019. The supplementary material can be found at
Categories: cs.CV
Related articles: Most relevant | Search more
arXiv:2105.00490 [cs.CV] (Published 2021-05-02)
Residual Enhanced Multi-Hypergraph Neural Network
arXiv:2006.07084 [cs.CV] (Published 2020-06-12)
A Face Preprocessing Approach for Improved DeepFake Detection
arXiv:1908.02671 [cs.CV] (Published 2019-08-07)
Dual-reference Age Synthesis