{"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/adversarially-slicing-generative-networks","title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","arxiv_id":"2301.12811","date":"2023-01-30","proceeding":null,"authors":["Yuhta Takida","Masaaki Imaizumi","Takashi Shibuya","Chieh-Hsin Lai","Toshimitsu Uesaka","Naoki Murata","Yuki Mitsufuji"],"abstract":"Generative adversarial networks (GANs) learn a target probability distribution by optimizing a generator and a discriminator with minimax objectives. This paper addresses the question of whether such optimization actually provides the generator with gradients that make its distribution close to the target distribution. We derive metrizable conditions, sufficient conditions for the discriminator to serve as the distance between the distributions by connecting the GAN formulation with the concept of sliced optimal transport. Furthermore, by leveraging these theoretical results, we propose a novel GAN training scheme, called slicing adversarial network (SAN). With only simple modifications, a broad class of existing GANs can be converted to SANs. Experiments on synthetic and image datasets support our theoretical results and the SAN's effectiveness as compared to usual GANs. Furthermore, we also apply SAN to StyleGAN-XL, which leads to state-of-the-art FID score amongst GANs for class conditional generation on ImageNet 256$\\times$256. Our implementation is available on https://ytakida.github.io/san.","url_abs":"https://arxiv.org/abs/2301.12811v4","url_pdf":"https://arxiv.org/pdf/2301.12811v4.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":"adversarially-slicing-generative-networks","repo_url":"https://github.com/sony/san","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-cifar-10","task":"Image Generation","dataset":"CIFAR-10","model":"StyleSAN-XL","rank_in_archive_order":3,"of":78,"metrics":{"FID":"1.36"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-ffhq-1024-x-1024","task":"Image Generation","dataset":"FFHQ 1024 x 1024","model":"StyleSAN-XL","rank_in_archive_order":1,"of":20,"metrics":{"FID":"1.61"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-ffhq-256-x-256","task":"Image Generation","dataset":"FFHQ 256 x 256","model":"StyleSAN-XL","rank_in_archive_order":1,"of":51,"metrics":{"FID":"1.68"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-ffhq-512-x-512","task":"Image Generation","dataset":"FFHQ 512 x 512","model":"StyleSAN-XL","rank_in_archive_order":1,"of":3,"metrics":{"FID":"1.77"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"StyleSAN-XL","rank_in_archive_order":52,"of":94,"metrics":{"FID":"2.14"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.12811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12811"}},"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":"deterministic:regex_extraction","url":"https://github.com/sony/san","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"7a97078d3969615b","entry":"SANLinear","repo":"sony/san","repo_kind":"official","path":"stylesan-xl/pg_modules/san_modules.py","file_url":"https://github.com/sony/san/blob/HEAD/stylesan-xl/pg_modules/san_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a97078d3969615b"}},{"code_sha256_prefix":"948aee5c76808012","entry":"_normalize","repo":"sony/san","repo_kind":"official","path":"stylesan-xl/pg_modules/san_modules.py","file_url":"https://github.com/sony/san/blob/HEAD/stylesan-xl/pg_modules/san_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"948aee5c76808012"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}