{"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/peergan-generative-adversarial-networks-with","title":"DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training","arxiv_id":"2101.07524","date":"2021-01-19","proceeding":null,"authors":["Jiaheng Wei","Minghao Liu","Jiahao Luo","Andrew Zhu","James Davis","Yang Liu"],"abstract":"In this paper, we introduce DuelGAN, a generative adversarial network (GAN) solution to improve the stability of the generated samples and to mitigate mode collapse. Built upon the Vanilla GAN's two-player game between the discriminator $D_1$ and the generator $G$, we introduce a peer discriminator $D_2$ to the min-max game. Similar to previous work using two discriminators, the first role of both $D_1$, $D_2$ is to distinguish between generated samples and real ones, while the generator tries to generate high-quality samples which are able to fool both discriminators. Different from existing methods, we introduce another game between $D_1$ and $D_2$ to discourage their agreement and therefore increase the level of diversity of the generated samples. This property alleviates the issue of early mode collapse by preventing $D_1$ and $D_2$ from converging too fast. We provide theoretical analysis for the equilibrium of the min-max game formed among $G, D_1, D_2$. We offer convergence behavior of DuelGAN as well as stability of the min-max game. It's worth mentioning that DuelGAN operates in the unsupervised setting, and the duel between $D_1$ and $D_2$ does not need any label supervision. Experiments results on a synthetic dataset and on real-world image datasets (MNIST, Fashion MNIST, CIFAR-10, STL-10, CelebA, VGG, and FFHQ) demonstrate that DuelGAN outperforms competitive baseline work in generating diverse and high-quality samples, while only introduces negligible computation cost.","url_abs":"https://arxiv.org/abs/2101.07524v3","url_pdf":"https://arxiv.org/pdf/2101.07524v3.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":[],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-cifar-10","task":"Image Generation","dataset":"CIFAR-10","model":"PeerGAN","rank_in_archive_order":56,"of":78,"metrics":{"FID":"21.55"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-celeba-64x64","task":"Image Generation","dataset":"CelebA 64x64","model":"PeerGAN","rank_in_archive_order":30,"of":39,"metrics":{"FID":"13.95"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-fashion-mnist","task":"Image Generation","dataset":"Fashion-MNIST","model":"PeerGAN","rank_in_archive_order":3,"of":7,"metrics":{"FID":"21.73"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-stl-10","task":"Image Generation","dataset":"STL-10","model":"PeerGAN","rank_in_archive_order":29,"of":31,"metrics":{"FID":"51.37"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}