PWGAN:Wasserstein GA Ns with Perceptual Loss for Mode Collapse
Generative adversarial network(GAN)plays an important part in image generation.It has great achievements trained on large scene data sets.However,for small scene data sets,we find that most of methods may lead to a mode collapse,which may repeatedly generate the same image with bad quality.To solve the problem,a novel Wasserstein Gen-erative Adversarial Networks with perceptual loss function(PWGAN)is proposed in this paper.The proposed approach could be better to reflect the characteristics of the ground truth and the generated samples,and combining with the training adversarial loss,PWGAN can produce a percep-tual realistic image.There are two benefits of PWGAN over state-of-the-art approaches on small scene data sets.First,PWGAN ensures the diversity of the generated samples,and basically solve mode collapse problem under the small scene data sets.Second,PWGAN enables the generator network quickly converge and improve training stability.Experimen-tal results show that the images generated by PWGAN have achieved better quality in visual effect and stability than state-of-the-art approaches.
GAN Image generation Perceptual loss Mode collapse Sta-bility
Xianyu Wu Canghong Shi Xiaojie Li Jia He Xi Wu Jiancheng Lv Jiliu Zhou
Chengdu University of Information Technology China School of Information Science and Technology Southwest Jiaotong University China Sichuan University China
国际会议
2019国图灵大会(ACM Turing Celebration conference-China 2019 )
成都
英文
941-947
2019-05-17(万方平台首次上网日期,不代表论文的发表时间)