{"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/faster-autoaugment-learning-augmentation","title":"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation","arxiv_id":"1911.06987","date":"2019-11-16","proceeding":"ECCV 2020 8","authors":["Ryuichiro Hataya","Jan Zdenek","Kazuki Yoshizoe","Hideki Nakayama"],"abstract":"Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms outperform hand-made strategies. Such methods employ black-box search algorithms over image transformations with continuous or discrete parameters and require a long time to obtain better strategies. In this paper, we propose a differentiable policy search pipeline for data augmentation, which is much faster than previous methods. We introduce approximate gradients for several transformation operations with discrete parameters as well as the differentiable mechanism for selecting operations. As the objective of training, we minimize the distance between the distributions of augmented data and the original data, which can be differentiated. We show that our method, Faster AutoAugment, achieves significantly faster searching than prior work without a performance drop.","url_abs":"https://arxiv.org/abs/1911.06987v1","url_pdf":"https://arxiv.org/pdf/1911.06987v1.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":"faster-autoaugment-learning-augmentation","repo_url":"https://github.com/moskomule/dda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[{"method_slug":"autoaugment","method_name":"AutoAugment"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-augmentation-on-cifar-10","task":"Data Augmentation","dataset":"CIFAR-10","model":"Shake-Shake (26 2×96d) (Faster AA)","rank_in_archive_order":1,"of":5,"metrics":{"Percentage error":"2"},"uses_additional_data":false},{"leaderboard":"/sota/data-augmentation-on-cifar-10","task":"Data Augmentation","dataset":"CIFAR-10","model":"Shake-Shake (26 2×112d) (Faster AA)","rank_in_archive_order":2,"of":5,"metrics":{"Percentage error":"2"},"uses_additional_data":false},{"leaderboard":"/sota/data-augmentation-on-cifar-10","task":"Data Augmentation","dataset":"CIFAR-10","model":"WideResNet-28-10 (Faster AA)","rank_in_archive_order":3,"of":5,"metrics":{"Percentage error":"2.6"},"uses_additional_data":false},{"leaderboard":"/sota/data-augmentation-on-cifar-10","task":"Data Augmentation","dataset":"CIFAR-10","model":"Shake-Shake (26 2×32d) (Faster AA)","rank_in_archive_order":4,"of":5,"metrics":{"Percentage error":"2.7"},"uses_additional_data":false},{"leaderboard":"/sota/data-augmentation-on-cifar-10","task":"Data Augmentation","dataset":"CIFAR-10","model":"WideResNet-40-2 (Faster AA)","rank_in_archive_order":5,"of":5,"metrics":{"Percentage error":"3.7"},"uses_additional_data":false},{"leaderboard":"/sota/data-augmentation-on-imagenet","task":"Data Augmentation","dataset":"ImageNet","model":"ResNet-50 (Faster AA)","rank_in_archive_order":16,"of":17,"metrics":{"Accuracy (%)":"76.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.06987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06987"}},"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/moskomule/dda","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"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":"1ccd9eba5721f000","entry":"get_gaussian_3x3kernel","repo":"moskomule/dda","repo_kind":"listed","path":"dda/kernels.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/kernels.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":"1ccd9eba5721f000"}},{"code_sha256_prefix":"c74fe1c3169c6c7e","entry":"get_gaussian_5x5kernel","repo":"moskomule/dda","repo_kind":"listed","path":"dda/kernels.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/kernels.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":"c74fe1c3169c6c7e"}},{"code_sha256_prefix":"168e865c2a5bfb4d","entry":"get_sharpness_kernel","repo":"moskomule/dda","repo_kind":"listed","path":"dda/kernels.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/kernels.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":"168e865c2a5bfb4d"}},{"code_sha256_prefix":"b4369762852f94d3","entry":"pil_function","repo":"moskomule/dda","repo_kind":"listed","path":"dda/pil.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/pil.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":"b4369762852f94d3"}},{"code_sha256_prefix":"90f7118023305b3b","entry":"shear_x","repo":"moskomule/dda","repo_kind":"listed","path":"dda/functional.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/functional.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":"90f7118023305b3b"}},{"code_sha256_prefix":"1bcc85675f7606d4","entry":"shear_x","repo":"moskomule/dda","repo_kind":"listed","path":"dda/pil.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/pil.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":"1bcc85675f7606d4"}},{"code_sha256_prefix":"8959fa6a39629fbc","entry":"shear_y","repo":"moskomule/dda","repo_kind":"listed","path":"dda/pil.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/pil.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":"8959fa6a39629fbc"}},{"code_sha256_prefix":"b67da72b4fb68fb1","entry":"ste","repo":"moskomule/dda","repo_kind":"listed","path":"dda/functional.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/functional.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":"b67da72b4fb68fb1"}},{"code_sha256_prefix":"f96aedd60a8e532e","entry":"tensor_function","repo":"moskomule/dda","repo_kind":"listed","path":"dda/functional.py","file_url":"https://github.com/moskomule/dda/blob/HEAD/dda/functional.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":"f96aedd60a8e532e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}