Cited By
View all- Wei TCao DZheng CYang Q(2020)A simulation-based few samples learning method for surface defect segmentationNeurocomputing10.1016/j.neucom.2020.06.090412(461-476)Online publication date: Oct-2020
PWGAN: wasserstein GANs with perceptual loss for mode collapse
Authors: 
Xianyu Wu, Canghong Shi, Xiaojie Li, Jia He, Xi Wu, Jiancheng Lv, Jiliu ZhouAuthors Info & Claims
Xianyu Wu, Canghong Shi, Xiaojie Li, Jia He, Xi Wu, Jiancheng Lv, Jiliu ZhouAuthors Info & ClaimsArticle No.: 151, Pages 1 - 7
Abstract
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 Generative 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 perceptual 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. Experimental results show that the images generated by PWGAN have achieved better quality in visual effect and stability than state-of-the-art approaches.
References
[1]
Mart<sup>.a</sup>n Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, and Michael Isard. 2016. TensorFlow: a system for large-scale machine learning. (2016).
[2]
Martin Arjovsky, Soumith Chintala, and Leon Bottou. 2017. Wasserstein GAN. arXiv: https://arxiv.org/abs/1701.07875 (2017).
[3]
Dongdong Chen, Jiancheng Lv, and Zhang Yi. 2018. Graph regularized Restricted Boltzmann Machine. IEEE Transactions on Neural Networks & Learning Systems 29, 6 (2018), 2651--2659.
[4]
G<sup>.</sup>®mez Pedro A Golbabaee M, Chen D. 2018. Geometry of Deep Learning for Magnetic Resonance Fingerprinting. In arXiv: https://arxiv.org/abs/1809.01749.
[5]
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In International Conference on Neural Information Processing Systems. 2672--2680.
[6]
Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron Courville. 2017. Improved Training of Wasserstein GANs. arXiv: https://arxiv.org/abs/1704.00028 (2017).
[7]
Thomas Kurbiel and Shahrzad Khaleghian. 2017. Training of Deep Neural Networks based on Distance Measures using RM-SProp. arXiv: https://arxiv.org/pdf/1708.01911 (2017).
[8]
Christian Ledig, Zehan Wang, Wenzhe Shi, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, and Alykhan Tejani. 2017. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In Computer Vision and Pattern Recognition. 105--114.
[9]
Chao Luo, Xiaojie Li, Lutao Wang, Jia He, Denggao Li, and Jiliu Zhou. 2018. How Does the Data set Affect CNN-based Image Classification Performance? 2018 5th International Conference on Systems and Informatics (ICSAI) (2018), 361--366.
[10]
Xudong Mao, Qing Li, Haoran Xie, Raymond Y. K. Lau, Zhen Wang, and Stephen Paul Smolley. 2016. Least Squares Generative Adversarial Networks. arXiv: https://arxiv.org/abs/1611.04076 (2016).
[11]
Alec Radford, Luke Metz, and Soumith Chintala. 2015. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. Computer Science (2015).
[12]
Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, and Honglak Lee. 2016. Generative adversarial text to image synthesis. In International Conference on International Conference on Machine Learning. 1060--1069.
[13]
Mehdi S. M Sajjadi, Bernhard Sch?lkopf, and Michael Hirsch. 2016. EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis. arXiv: https://arxiv.org/abs/1612.07919 (2016), 4501--4510.
[14]
Shuang Wu, Guoqi Li, Lei Deng, Liu Liu, Yuan Xie, and Luping Shi. 2018. L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks. arXiv: https://arxiv.org/abs/1802.09769 (2018).
[15]
Xianyu Wu, Xiaojie Li, Jia He, Xi Wu, and Imran Mumtaz. 2019. Generative Adversarial Networks with Enhanced Symmetric Residual Units for Single Image Super-Resolution. International Conference on Multimedia Modeling (2019), 483--494.
[16]
Q. Yang, P. Yan, Y. Zhang, H. Yu, Y. Shi, X. Mou, M. K. Kalra, Y. Zhang, L. Sun, and G. Wang. 2017. Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss. IEEE Transactions on Medical Imaging PP, 99 (2017), 1--1.
[17]
Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. 2015. LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. Computer Science (2015).
[18]
Jun Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In IEEE International Conference on Computer Vision. 2242--2251.
Recommendations
On the convergence and mode collapse of GAN
SA '18: SIGGRAPH Asia 2018 Technical BriefsGenerative adversarial network (GAN) is a powerful generative model. However, it suffers from several problems, such as convergence instability and mode collapse. To overcome these drawbacks, this paper presents a novel architecture of GAN, which ...
Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions
Generative Adversarial Networks (GANs) is a novel class of deep generative models that has recently gained significant attention. GANs learn complex and high-dimensional distributions implicitly over images, audio, and data. However, there exist major ...
Towards the Gradient Vanishing, Divergence Mismatching and Mode Collapse of Generative Adversarial Nets
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementGenerative adversarial network (GAN) is a powerful generative model. However, it suffers from gradient vanishing, divergence mismatching and mode collapse. To overcome these problems, we propose a novel GAN, which consists of one generator G and two ...
Comments
Information & Contributors
Information
Published In
May 2019
963 pages
ISBN:9781450371582
DOI:10.1145/3321408
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 17 May 2019
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
ACM TURC 2019
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 113Total Downloads
- Downloads (Last 12 months)17
- Downloads (Last 6 weeks)0
Reflects downloads up to 26 Jul 2024
Other Metrics
Citations
Cited By
View all- Wei TCao DZheng CYang Q(2020)A simulation-based few samples learning method for surface defect segmentationNeurocomputing10.1016/j.neucom.2020.06.090412(461-476)Online publication date: Oct-2020
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in