{"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/you-only-need-adversarial-supervision-for-1","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","arxiv_id":"2012.04781","date":"2020-12-08","proceeding":"ICLR 2021 1","authors":["Vadim Sushko","Edgar Schönfeld","Dan Zhang","Juergen Gall","Bernt Schiele","Anna Khoreva"],"abstract":"Despite their recent successes, GAN models for semantic image synthesis still suffer from poor image quality when trained with only adversarial supervision. Historically, additionally employing the VGG-based perceptual loss has helped to overcome this issue, significantly improving the synthesis quality, but at the same time limiting the progress of GAN models for semantic image synthesis. In this work, we propose a novel, simplified GAN model, which needs only adversarial supervision to achieve high quality results. We re-design the discriminator as a semantic segmentation network, directly using the given semantic label maps as the ground truth for training. By providing stronger supervision to the discriminator as well as to the generator through spatially- and semantically-aware discriminator feedback, we are able to synthesize images of higher fidelity with better alignment to their input label maps, making the use of the perceptual loss superfluous. Moreover, we enable high-quality multi-modal image synthesis through global and local sampling of a 3D noise tensor injected into the generator, which allows complete or partial image change. We show that images synthesized by our model are more diverse and follow the color and texture distributions of real images more closely. We achieve an average improvement of $6$ FID and $5$ mIoU points over the state of the art across different datasets using only adversarial supervision.","url_abs":"https://arxiv.org/abs/2012.04781v3","url_pdf":"https://arxiv.org/pdf/2012.04781v3.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":"you-only-need-adversarial-supervision-for-1","repo_url":"https://github.com/boschresearch/OASIS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"oasis","method_name":"OASIS"}],"datasets_introduced":[],"methods_introduced":[{"slug":"oasis","name":"OASIS","full_name":"OASIS"}],"results":[{"leaderboard":"/sota/image-to-image-translation-on-ade20k-labels","task":"Image-to-Image Translation","dataset":"ADE20K Labels-to-Photos","model":"OASIS","rank_in_archive_order":5,"of":16,"metrics":{"FID":"28.3","LPIPS":"0.265","mIoU":"48.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-ade20k-outdoor","task":"Image-to-Image Translation","dataset":"ADE20K-Outdoor Labels-to-Photos","model":"OASIS","rank_in_archive_order":2,"of":7,"metrics":{"FID":"48.6","mIoU":"40.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-coco-stuff","task":"Image-to-Image Translation","dataset":"COCO-Stuff Labels-to-Photos","model":"OASIS","rank_in_archive_order":6,"of":15,"metrics":{"FID":"17.0","mIoU":"44.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-cityscapes","task":"Image-to-Image Translation","dataset":"Cityscapes Labels-to-Photo","model":"OASIS","rank_in_archive_order":3,"of":21,"metrics":{"FID":"47.7","LPIPS":"0.275","mIoU":"69.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.04781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04781"}},"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/boschresearch/OASIS","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":7,"samples":[{"code_sha256_prefix":"6aa177345c607564","entry":"get_spectral_norm","repo":"boschresearch/OASIS","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/boschresearch/OASIS/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6aa177345c607564"}},{"code_sha256_prefix":"e8bd9b95b121b2d8","entry":"OASIS_Generator","repo":"boschresearch/OASIS","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/boschresearch/OASIS/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e8bd9b95b121b2d8"}},{"code_sha256_prefix":"82a67c279130d1cc","entry":"ResnetBlock_with_SPADE","repo":"boschresearch/OASIS","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/boschresearch/OASIS/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"82a67c279130d1cc"}},{"code_sha256_prefix":"1dbb4eb3753005ea","entry":"SPADE","repo":"boschresearch/OASIS","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/boschresearch/OASIS/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1dbb4eb3753005ea"}},{"code_sha256_prefix":"f8702e039957dd78","entry":"SynchronizedBatchNorm2d","repo":"boschresearch/OASIS","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/boschresearch/OASIS/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f8702e039957dd78"}},{"code_sha256_prefix":"978474dc09509a4f","entry":"_SynchronizedBatchNorm","repo":"boschresearch/OASIS","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/boschresearch/OASIS/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"978474dc09509a4f"}},{"code_sha256_prefix":"b5fffb8bee3c2968","entry":"get_norm_layer","repo":"boschresearch/OASIS","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/boschresearch/OASIS/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b5fffb8bee3c2968"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}