{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deep-autoaugment-1","title":"Deep AutoAugment","arxiv_id":"2203.06172","date":"2022-03-11","proceeding":null,"authors":["Yu Zheng","Zhi Zhang","Shen Yan","Mi Zhang"],"abstract":"While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human priors. In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA). DeepAA progressively builds a multi-layer data augmentation pipeline from scratch by stacking augmentation layers one at a time until reaching convergence. For each augmentation layer, the policy is optimized to maximize the cosine similarity between the gradients of the original and augmented data along the direction with low variance. Our experiments show that even without default augmentations, we can learn an augmentation policy that achieves strong performance with that of previous works. Extensive ablation studies show that the regularized gradient matching is an effective search method for data augmentation policies. Our code is available at: https://github.com/MSU-MLSys-Lab/DeepAA .","url_abs":"https://arxiv.org/abs/2203.06172v2","url_pdf":"https://arxiv.org/pdf/2203.06172v2.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":"deep-autoaugment-1","repo_url":"https://github.com/msu-mlsys-lab/deepaa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"fast-autoaugment","method_name":"Fast AutoAugment"},{"method_slug":"randaugment","method_name":"RandAugment"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/data-augmentation-on-imagenet","task":"Data Augmentation","dataset":"ImageNet","model":"ResNet-200 (DeepAA)","rank_in_archive_order":2,"of":17,"metrics":{"Accuracy (%)":"81.32"},"uses_additional_data":false},{"leaderboard":"/sota/data-augmentation-on-imagenet","task":"Data Augmentation","dataset":"ImageNet","model":"ResNet-50 (DeepAA)","rank_in_archive_order":7,"of":17,"metrics":{"Accuracy (%)":"78.30"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.06172","atlas_url":"https://app.syntology.ai/?focus=2203.06172","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.06172"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.06172\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.06172"},"call":"get_concepts_for_paper(arxiv_id=\"2203.06172\")"}],"by_repo":[{"repo":"msu-mlsys-lab/deepaa","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"38e58ef87ec20765ca1cc0ea2a20c61af07021ad5c430d120418ee476b5cd8d8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}