{"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/training-generative-adversarial-networks-with-1","title":"Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation","arxiv_id":"1810.04714","date":"2018-10-10","proceeding":null,"authors":["Hao-Wen Dong","Yi-Hsuan Yang"],"abstract":"We propose the BinaryGAN, a novel generative adversarial network (GAN) that\nuses binary neurons at the output layer of the generator. We employ the\nsigmoid-adjusted straight-through estimators to estimate the gradients for the\nbinary neurons and train the whole network by end-to-end backpropogation. The\nproposed model is able to directly generate binary-valued predictions at test\ntime. We implement such a model to generate binarized MNIST digits and\nexperimentally compare the performance for different types of binary neurons,\nGAN objectives and network architectures. Although the results are still\npreliminary, we show that it is possible to train a GAN that has binary neurons\nand that the use of gradient estimators can be a promising direction for\nmodeling discrete distributions with GANs. For reproducibility, the source code\nis available at https://github.com/salu133445/binarygan .","url_abs":"http://arxiv.org/abs/1810.04714v1","url_pdf":"http://arxiv.org/pdf/1810.04714v1.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":"training-generative-adversarial-networks-with-1","repo_url":"https://github.com/salu133445/binarygan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1810.04714","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}