{"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/madan-multi-source-adversarial-domain","title":"MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation","arxiv_id":"2003.00820","date":"2020-02-19","proceeding":null,"authors":["Sicheng Zhao","Bo Li","Xiangyu Yue","Pengfei Xu","Kurt Keutzer"],"abstract":"Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain. Since the labeled data may be collected from multiple sources, multi-source domain adaptation (MDA) has attracted increasing attention. Recent MDA methods do not consider the pixel-level alignment between sources and target or the misalignment across different sources. In this paper, we propose a novel MDA framework to address these challenges. Specifically, we design an end-to-end Multi-source Adversarial Domain Aggregation Network (MADAN). First, an adapted domain is generated for each source with dynamic semantic consistency while aligning towards the target at the pixel-level cycle-consistently. Second, sub-domain aggregation discriminator and cross-domain cycle discriminator are proposed to make different adapted domains more closely aggregated. Finally, feature-level alignment is performed between the aggregated domain and the target domain while training the task network. For the segmentation adaptation, we further enforce category-level alignment and incorporate context-aware generation, which constitutes MADAN+. We conduct extensive MDA experiments on digit recognition, object classification, and simulation-to-real semantic segmentation. The results demonstrate that the proposed MADAN and MANDA+ models outperform state-of-the-art approaches by a large margin.","url_abs":"https://arxiv.org/abs/2003.00820v1","url_pdf":"https://arxiv.org/pdf/2003.00820v1.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":"madan-multi-source-adversarial-domain","repo_url":"https://github.com/Luodian/MADAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"madan-multi-source-adversarial-domain","repo_url":"https://github.com/MindSpore-scientific/code-6/tree/main/multi-adversarial-domain-adaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.00820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00820"}},"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/Luodian/MADAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-6/tree/main/multi-adversarial-domain-adaptation","reach":null}],"summary":{"ran_honours":1,"ran":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":1,"samples":[{"code_sha256_prefix":"21b188a4406f5a30","entry":"to_tensor_raw","repo":"Luodian/MADAN","repo_kind":"official","path":"scripts/train_fcn.py","file_url":"https://github.com/Luodian/MADAN/blob/HEAD/scripts/train_fcn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21b188a4406f5a30"}},{"code_sha256_prefix":"e4a4daa9f574a3a3","entry":"ImagePool","repo":"Luodian/MADAN","repo_kind":"official","path":"cyclegan/models/multi_cycle_gan_semantic_model.py","file_url":"https://github.com/Luodian/MADAN/blob/HEAD/cyclegan/models/multi_cycle_gan_semantic_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4a4daa9f574a3a3"}},{"code_sha256_prefix":"ed35488af2926773","entry":"supervised_loss","repo":"Luodian/MADAN","repo_kind":"official","path":"scripts/train_fcn.py","file_url":"https://github.com/Luodian/MADAN/blob/HEAD/scripts/train_fcn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed35488af2926773"}},{"code_sha256_prefix":"aa07d24d8087a985","entry":"BaseModel","repo":"Luodian/MADAN","repo_kind":"official","path":"cyclegan/models/multi_cycle_gan_semantic_model.py","file_url":"https://github.com/Luodian/MADAN/blob/HEAD/cyclegan/models/multi_cycle_gan_semantic_model.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":"aa07d24d8087a985"}},{"code_sha256_prefix":"aac5528a8d4646be","entry":"CycleGANSemanticModel","repo":"Luodian/MADAN","repo_kind":"official","path":"cyclegan/models/multi_cycle_gan_semantic_model.py","file_url":"https://github.com/Luodian/MADAN/blob/HEAD/cyclegan/models/multi_cycle_gan_semantic_model.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":"aac5528a8d4646be"}},{"code_sha256_prefix":"2efe87863253f8ba","entry":"get_model","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2efe87863253f8ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}