{"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/adversarial-training-of-variational-auto","title":"Adversarial Training of Variational Auto-encoders for High Fidelity Image Generation","arxiv_id":"1804.10323","date":"2018-04-27","proceeding":null,"authors":["Salman H. Khan","Munawar Hayat","Nick Barnes"],"abstract":"Variational auto-encoders (VAEs) provide an attractive solution to image\ngeneration problem. However, they tend to produce blurred and over-smoothed\nimages due to their dependence on pixel-wise reconstruction loss. This paper\nintroduces a new approach to alleviate this problem in the VAE based generative\nmodels. Our model simultaneously learns to match the data, reconstruction loss\nand the latent distributions of real and fake images to improve the quality of\ngenerated samples. To compute the loss distributions, we introduce an\nauto-encoder based discriminator model which allows an adversarial learning\nprocedure. The discriminator in our model also provides perceptual guidance to\nthe VAE by matching the learned similarity metric of the real and fake samples\nin the latent space. To stabilize the overall training process, our model uses\nan error feedback approach to maintain the equilibrium between competing\nnetworks in the model. Our experiments show that the generated samples from our\nproposed model exhibit a diverse set of attributes and facial expressions and\nscale up to high-resolution images very well.","url_abs":"http://arxiv.org/abs/1804.10323v1","url_pdf":"http://arxiv.org/pdf/1804.10323v1.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":"adversarial-training-of-variational-auto","repo_url":"https://github.com/OsvaldN/APS360_Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}