15 November 2017 Structure guided GANs
Author Affiliations +
Proceedings Volume 10605, LIDAR Imaging Detection and Target Recognition 2017; 106052U (2017) https://doi.org/10.1117/12.2294482
Event: LIDAR Imaging Detection and Target Recognition 2017, 2017, Changchun, China
Generative adversarial networks (GANs) has achieved success in many fields. However, there are some samples generated by many GAN-based works, whose structure is ambiguous. In this work, we propose Structure Guided GANs that introduce structural similar into GANs to overcome the problem. In order to achieve our goal, we introduce an encoder and a decoder into a generator to design a new generator and take real samples as part of the input of a generator. And we modify the loss function of the generator accordingly. By comparison with WGAN, experimental results show that our proposed method overcomes largely sample structure ambiguous and can generate higher quality samples.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Feidao Cao, Feidao Cao, Huaici Zhao, Huaici Zhao, Pengfei Liu, Pengfei Liu, "Structure guided GANs", Proc. SPIE 10605, LIDAR Imaging Detection and Target Recognition 2017, 106052U (15 November 2017); doi: 10.1117/12.2294482; https://doi.org/10.1117/12.2294482

Back to Top