{"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/triple-generative-adversarial-networks","title":"Triple Generative Adversarial Networks","arxiv_id":"1912.09784","date":"2019-12-20","proceeding":null,"authors":["Chongxuan Li","Kun Xu","Jiashuo Liu","Jun Zhu","Bo Zhang"],"abstract":"We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN). The generator and the classifier characterize the conditional distributions between images and labels to perform conditional generation and classification, respectively. The discriminator solely focuses on identifying fake image-label pairs. Under a nonparametric assumption, we prove the unique equilibrium of the game is that the distributions characterized by the generator and the classifier converge to the data distribution. As a byproduct of the three-player mechanism, Triple-GAN is flexible to incorporate different semi-supervised classifiers and GAN architectures. We evaluate Triple-GAN in two challenging settings, namely, semi-supervised learning and the extreme low data regime. In both settings, Triple-GAN can achieve excellent classification results and generate meaningful samples in a specific class simultaneously. In particular, using a commonly adopted 13-layer CNN classifier, Triple-GAN outperforms extensive semi-supervised learning methods substantially on more than 10 benchmarks no matter data augmentation is applied or not.","url_abs":"https://arxiv.org/abs/1912.09784v2","url_pdf":"https://arxiv.org/pdf/1912.09784v2.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":"triple-generative-adversarial-networks","repo_url":"https://github.com/taufikxu/Triple-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-11","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 1000 Labels","model":"Triple-GAN-V2 (ResNet-26)","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"91.59"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-11","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 1000 Labels","model":"Triple-GAN-V2 (CNN-13)","rank_in_archive_order":6,"of":9,"metrics":{"Accuracy":"85.00"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-11","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 1000 Labels","model":"Triple-GAN-V2 (CNN-13, no aug)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"81.81"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"Triple-GAN-V2 (ResNet-26)","rank_in_archive_order":34,"of":49,"metrics":{"Percentage error":"6.54"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"Triple-GAN-V2 (CNN-13)","rank_in_archive_order":40,"of":49,"metrics":{"Percentage error":"10.01"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"Triple-GAN-V2 (CNN-13, no aug)","rank_in_archive_order":46,"of":49,"metrics":{"Percentage error":"12.41"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn","task":"Semi-Supervised Image Classification","dataset":"SVHN, 1000 labels","model":"Triple-GAN-V2 (CNN-13)","rank_in_archive_order":8,"of":17,"metrics":{"Accuracy":"96.55"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn","task":"Semi-Supervised Image Classification","dataset":"SVHN, 1000 labels","model":"Triple-GAN-V2 (CNN-13, no aug)","rank_in_archive_order":14,"of":17,"metrics":{"Accuracy":"96.04"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-1","task":"Semi-Supervised Image Classification","dataset":"SVHN, 250 Labels","model":"Triple-GAN-V2 (CNN-13)","rank_in_archive_order":6,"of":15,"metrics":{"Accuracy":"96.52"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-1","task":"Semi-Supervised Image Classification","dataset":"SVHN, 250 Labels","model":"Triple-GAN-V2 (CNN-13, no aug)","rank_in_archive_order":9,"of":15,"metrics":{"Accuracy":"95.81"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-3","task":"Semi-Supervised Image Classification","dataset":"SVHN, 500 Labels","model":"Triple-GAN-V2 (CNN-13)","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"96.39"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-3","task":"Semi-Supervised Image Classification","dataset":"SVHN, 500 Labels","model":"Triple-GAN-V2 (CNN-13, no aug)","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"96.16"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.09784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.09784"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/taufikxu/Triple-GAN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"335de19ad40af504","entry":"get_inception_score","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/eval_inception_score.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/eval_inception_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"335de19ad40af504"}},{"code_sha256_prefix":"069122bd5268cc56","entry":"linear_rampup","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/loss_cla.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/loss_cla.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"069122bd5268cc56"}},{"code_sha256_prefix":"d93071d043de21d5","entry":"loss_cross_entropy_ele","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/loss_triplegan.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/loss_triplegan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d93071d043de21d5"}},{"code_sha256_prefix":"ae6e6873858f8ddf","entry":"loss_dcgan_dis","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/loss_gan.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/loss_gan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae6e6873858f8ddf"}},{"code_sha256_prefix":"98b3c5751e09b90b","entry":"loss_dcgan_gen","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/loss_gan.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/loss_gan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98b3c5751e09b90b"}},{"code_sha256_prefix":"1abccc079f315676","entry":"loss_hinge_dis","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/loss_gan.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/loss_gan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1abccc079f315676"}},{"code_sha256_prefix":"2d9f6f3c7fd20be7","entry":"sigmoid_rampdown","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/loss_cla.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/loss_cla.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d9f6f3c7fd20be7"}},{"code_sha256_prefix":"f8f34f7f96b293a1","entry":"sigmoid_rampup","repo":"taufikxu/Triple-GAN","repo_kind":"official","path":"library/loss_cla.py","file_url":"https://github.com/taufikxu/Triple-GAN/blob/HEAD/library/loss_cla.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8f34f7f96b293a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}