{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generative-adversarial-networks-with-decoder","title":"Generative Adversarial Networks with Decoder-Encoder Output Noise","arxiv_id":"1807.03923","date":"2018-07-11","proceeding":null,"authors":["Guoqiang Zhong","Wei Gao","Yongbin Liu","Youzhao Yang"],"abstract":"In recent years, research on image generation methods has been developing\nfast. The auto-encoding variational Bayes method (VAEs) was proposed in 2013,\nwhich uses variational inference to learn a latent space from the image\ndatabase and then generates images using the decoder. The generative\nadversarial networks (GANs) came out as a promising framework, which uses\nadversarial training to improve the generative ability of the generator.\nHowever, the generated pictures by GANs are generally blurry. The deep\nconvolutional generative adversarial networks (DCGANs) were then proposed to\nleverage the quality of generated images. Since the input noise vectors are\nrandomly sampled from a Gaussian distribution, the generator has to map from a\nwhole normal distribution to the images. This makes DCGANs unable to reflect\nthe inherent structure of the training data. In this paper, we propose a novel\ndeep model, called generative adversarial networks with decoder-encoder output\nnoise (DE-GANs), which takes advantage of both the adversarial training and the\nvariational Bayesain inference to improve the performance of image generation.\nDE-GANs use a pre-trained decoder-encoder architecture to map the random\nGaussian noise vectors to informative ones and pass them to the generator of\nthe adversarial networks. Since the decoder-encoder architecture is trained by\nthe same images as the generators, the output vectors could carry the intrinsic\ndistribution information of the original images. Moreover, the loss function of\nDE-GANs is different from GANs and DCGANs. A hidden-space loss function is\nadded to the adversarial loss function to enhance the robustness of the model.\nExtensive empirical results show that DE-GANs can accelerate the convergence of\nthe adversarial training process and improve the quality of the generated\nimages.","url_abs":"http://arxiv.org/abs/1807.03923v1","url_pdf":"http://arxiv.org/pdf/1807.03923v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generative-adversarial-networks-with-decoder","repo_url":"https://github.com/Aminsaffar/DE-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}