{"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/data-augmentation-generative-adversarial","title":"Data Augmentation Generative Adversarial Networks","arxiv_id":"1711.04340","date":"2017-11-12","proceeding":"ICLR 2018 1","authors":["Antreas Antoniou","Amos Storkey","Harrison Edwards"],"abstract":"Effective training of neural networks requires much data. In the low-data\nregime, parameters are underdetermined, and learnt networks generalise poorly.\nData Augmentation alleviates this by using existing data more effectively.\nHowever standard data augmentation produces only limited plausible alternative\ndata. Given there is potential to generate a much broader set of augmentations,\nwe design and train a generative model to do data augmentation. The model,\nbased on image conditional Generative Adversarial Networks, takes data from a\nsource domain and learns to take any data item and generalise it to generate\nother within-class data items. As this generative process does not depend on\nthe classes themselves, it can be applied to novel unseen classes of data. We\nshow that a Data Augmentation Generative Adversarial Network (DAGAN) augments\nstandard vanilla classifiers well. We also show a DAGAN can enhance few-shot\nlearning systems such as Matching Networks. We demonstrate these approaches on\nOmniglot, on EMNIST having learnt the DAGAN on Omniglot, and VGG-Face data. In\nour experiments we can see over 13% increase in accuracy in the low-data regime\nexperiments in Omniglot (from 69% to 82%), EMNIST (73.9% to 76%) and VGG-Face\n(4.5% to 12%); in Matching Networks for Omniglot we observe an increase of 0.5%\n(from 96.9% to 97.4%) and an increase of 1.8% in EMNIST (from 59.5% to 61.3%).","url_abs":"http://arxiv.org/abs/1711.04340v3","url_pdf":"http://arxiv.org/pdf/1711.04340v3.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":"data-augmentation-generative-adversarial","repo_url":"https://github.com/AntreasAntoniou/DAGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"data-augmentation-generative-adversarial","repo_url":"https://github.com/BilcSergiu/DAGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"data-augmentation-generative-adversarial","repo_url":"https://github.com/amurthy1/dagan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"data-augmentation-generative-adversarial","repo_url":"https://github.com/amurthy1/dagan_torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"data-augmentation-generative-adversarial","repo_url":"https://github.com/gitaar9/MLDAGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"data-augmentation-generative-adversarial","repo_url":"https://github.com/hy-zpg/DAGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"data-augmentation-generative-adversarial","repo_url":"https://github.com/namepen/AI_school_proj","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":null,"task_name":"Generative Adversarial Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.04340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.04340"}},"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/BilcSergiu/DAGAN","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amurthy1/dagan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amurthy1/dagan_torch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gitaar9/MLDAGAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hy-zpg/DAGAN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/namepen/AI_school_proj","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AntreasAntoniou/DAGAN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":5,"ran":1,"repositories":2}},"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":"e73857dab63b5298","entry":"remove_duplicates","repo":"AntreasAntoniou/DAGAN","repo_kind":"listed","path":"dagan_architectures.py","file_url":"https://github.com/AntreasAntoniou/DAGAN/blob/HEAD/dagan_architectures.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e73857dab63b5298"}},{"code_sha256_prefix":"a44ccc77617c31fb","entry":"get_args","repo":"amurthy1/dagan","repo_kind":"listed","path":"utils/parser_util.py","file_url":"https://github.com/amurthy1/dagan/blob/HEAD/utils/parser_util.py","link_basis":"harvester_set","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":"a44ccc77617c31fb"}},{"code_sha256_prefix":"ee023c21ffe38ef3","entry":"lerp","repo":"AntreasAntoniou/DAGAN","repo_kind":"listed","path":"utils/interpolations.py","file_url":"https://github.com/AntreasAntoniou/DAGAN/blob/HEAD/utils/interpolations.py","link_basis":"harvester_set","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":"ee023c21ffe38ef3"}},{"code_sha256_prefix":"2491fa1841f23907","entry":"lerp_gaussian","repo":"AntreasAntoniou/DAGAN","repo_kind":"listed","path":"utils/interpolations.py","file_url":"https://github.com/AntreasAntoniou/DAGAN/blob/HEAD/utils/interpolations.py","link_basis":"harvester_set","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":"2491fa1841f23907"}},{"code_sha256_prefix":"9c1b90f679a7f761","entry":"slerp","repo":"AntreasAntoniou/DAGAN","repo_kind":"listed","path":"utils/interpolations.py","file_url":"https://github.com/AntreasAntoniou/DAGAN/blob/HEAD/utils/interpolations.py","link_basis":"harvester_set","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":"9c1b90f679a7f761"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}