{"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/designing-data-augmentation-for-simulating","title":"Selecting Data Augmentation for Simulating Interventions","arxiv_id":"2005.01856","date":"2020-05-04","proceeding":null,"authors":["Maximilian Ilse","Jakub M. Tomczak","Patrick Forré"],"abstract":"Machine learning models trained with purely observational data and the principle of empirical risk minimization \\citep{vapnik_principles_1992} can fail to generalize to unseen domains. In this paper, we focus on the case where the problem arises through spurious correlation between the observed domains and the actual task labels. We find that many domain generalization methods do not explicitly take this spurious correlation into account. Instead, especially in more application-oriented research areas like medical imaging or robotics, data augmentation techniques that are based on heuristics are used to learn domain invariant features. To bridge the gap between theory and practice, we develop a causal perspective on the problem of domain generalization. We argue that causal concepts can be used to explain the success of data augmentation by describing how they can weaken the spurious correlation between the observed domains and the task labels. We demonstrate that data augmentation can serve as a tool for simulating interventional data. We use these theoretical insights to derive a simple algorithm that is able to select data augmentation techniques that will lead to better domain generalization.","url_abs":"https://arxiv.org/abs/2005.01856v4","url_pdf":"https://arxiv.org/pdf/2005.01856v4.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":"designing-data-augmentation-for-simulating","repo_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.01856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.01856"}},"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/AMLab-Amsterdam/DataAugmentationInterventions","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"63ca8fa8e387f93c","entry":"caffenet","repo":"AMLab-Amsterdam/DataAugmentationInterventions","repo_kind":"official","path":"PACS/model_alexnet_caffe.py","file_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions/blob/HEAD/PACS/model_alexnet_caffe.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":"63ca8fa8e387f93c"}},{"code_sha256_prefix":"4649d4b3df7ca1e1","entry":"caffenet_fc7","repo":"AMLab-Amsterdam/DataAugmentationInterventions","repo_kind":"official","path":"PACS/model_alexnet_caffe.py","file_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions/blob/HEAD/PACS/model_alexnet_caffe.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":"4649d4b3df7ca1e1"}},{"code_sha256_prefix":"f32dcbf27897f428","entry":"caffenet_gap","repo":"AMLab-Amsterdam/DataAugmentationInterventions","repo_kind":"official","path":"PACS/model_alexnet_caffe.py","file_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions/blob/HEAD/PACS/model_alexnet_caffe.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":"f32dcbf27897f428"}},{"code_sha256_prefix":"6c830c598efe5902","entry":"test","repo":"AMLab-Amsterdam/DataAugmentationInterventions","repo_kind":"official","path":"PACS/fine_tune_alexnet.py","file_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions/blob/HEAD/PACS/fine_tune_alexnet.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":"6c830c598efe5902"}},{"code_sha256_prefix":"a1c542ac49f80bd6","entry":"test","repo":"AMLab-Amsterdam/DataAugmentationInterventions","repo_kind":"official","path":"PACS/fine_tune_alexnet_domain_classifier.py","file_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions/blob/HEAD/PACS/fine_tune_alexnet_domain_classifier.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":"a1c542ac49f80bd6"}},{"code_sha256_prefix":"e5b4aa10ff210951","entry":"train","repo":"AMLab-Amsterdam/DataAugmentationInterventions","repo_kind":"official","path":"PACS/fine_tune_alexnet.py","file_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions/blob/HEAD/PACS/fine_tune_alexnet.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":"e5b4aa10ff210951"}},{"code_sha256_prefix":"90a975015834910a","entry":"train","repo":"AMLab-Amsterdam/DataAugmentationInterventions","repo_kind":"official","path":"PACS/fine_tune_alexnet_domain_classifier.py","file_url":"https://github.com/AMLab-Amsterdam/DataAugmentationInterventions/blob/HEAD/PACS/fine_tune_alexnet_domain_classifier.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":"90a975015834910a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}