{"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/adversarial-bayesian-augmentation-for-single","title":"Adversarial Bayesian Augmentation for Single-Source Domain Generalization","arxiv_id":"2307.09520","date":"2023-07-18","proceeding":"ICCV 2023 1","authors":["Sheng Cheng","Tejas Gokhale","Yezhou Yang"],"abstract":"Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings. As such data augmentation is a critical component of domain generalization methods that seek to address this problem. We present Adversarial Bayesian Augmentation (ABA), a novel algorithm that learns to generate image augmentations in the challenging single-source domain generalization setting. ABA draws on the strengths of adversarial learning and Bayesian neural networks to guide the generation of diverse data augmentations -- these synthesized image domains aid the classifier in generalizing to unseen domains. We demonstrate the strength of ABA on several types of domain shift including style shift, subpopulation shift, and shift in the medical imaging setting. ABA outperforms all previous state-of-the-art methods, including pre-specified augmentations, pixel-based and convolutional-based augmentations.","url_abs":"https://arxiv.org/abs/2307.09520v2","url_pdf":"https://arxiv.org/pdf/2307.09520v2.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":"adversarial-bayesian-augmentation-for-single","repo_url":"https://github.com/shengcheng/aba","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"photo-to-rest-generalization","task_name":"Photo to Rest Generalization"},{"task_slug":"single-source-domain-generalization","task_name":"Single-Source Domain Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/photo-to-rest-generalization-on-pacs","task":"Photo to Rest Generalization","dataset":"PACS","model":"ABA (ResNet18)","rank_in_archive_order":5,"of":8,"metrics":{"Accuracy":"59.04"},"uses_additional_data":false},{"leaderboard":"/sota/single-source-domain-generalization-on-digits","task":"Single-Source Domain Generalization","dataset":"Digits-five","model":"ABA (LeNet)","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"76.72"},"uses_additional_data":false},{"leaderboard":"/sota/single-source-domain-generalization-on-pacs","task":"Single-Source Domain Generalization","dataset":"PACS","model":"ABA (ResNet18)","rank_in_archive_order":7,"of":10,"metrics":{"Accuracy":"66.36"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.09520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09520"}},"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/shengcheng/aba","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/shengcheng/ABA","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"7bbb38d4cf0ca988","entry":"asarray_and_reshape","repo":"shengcheng/ABA","repo_kind":"official","path":"trainer_bnn.py","file_url":"https://github.com/shengcheng/ABA/blob/HEAD/trainer_bnn.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":"7bbb38d4cf0ca988"}},{"code_sha256_prefix":"91e4bc52f793097b","entry":"calculate_kl","repo":"shengcheng/ABA","repo_kind":"official","path":"lib/networks/bayes_cnn.py","file_url":"https://github.com/shengcheng/ABA/blob/HEAD/lib/networks/bayes_cnn.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91e4bc52f793097b"}},{"code_sha256_prefix":"f709e785d2ca20cf","entry":"get_exp_name","repo":"shengcheng/ABA","repo_kind":"official","path":"trainer_bnn.py","file_url":"https://github.com/shengcheng/ABA/blob/HEAD/trainer_bnn.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":"f709e785d2ca20cf"}},{"code_sha256_prefix":"53831f37e3379def","entry":"t2s","repo":"shengcheng/ABA","repo_kind":"official","path":"trainer_bnn.py","file_url":"https://github.com/shengcheng/ABA/blob/HEAD/trainer_bnn.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":"53831f37e3379def"}},{"code_sha256_prefix":"39f9fa02ce767511","entry":"get_dataset","repo":"shengcheng/ABA","repo_kind":"official","path":"lib/datasets/data_helper.py","file_url":"https://github.com/shengcheng/ABA/blob/HEAD/lib/datasets/data_helper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"39f9fa02ce767511"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}