{"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/autodo-robust-autoaugment-for-biased-data","title":"AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation","arxiv_id":"2103.05863","date":"2021-03-10","proceeding":"CVPR 2021 1","authors":["Denis Gudovskiy","Luca Rigazio","Shun Ishizaka","Kazuki Kozuka","Sotaro Tsukizawa"],"abstract":"AutoAugment has sparked an interest in automated augmentation methods for deep learning models. These methods estimate image transformation policies for train data that improve generalization to test data. While recent papers evolved in the direction of decreasing policy search complexity, we show that those methods are not robust when applied to biased and noisy data. To overcome these limitations, we reformulate AutoAugment as a generalized automated dataset optimization (AutoDO) task that minimizes the distribution shift between test data and distorted train dataset. In our AutoDO model, we explicitly estimate a set of per-point hyperparameters to flexibly change distribution of train data. In particular, we include hyperparameters for augmentation, loss weights, and soft-labels that are jointly estimated using implicit differentiation. We develop a theoretical probabilistic interpretation of this framework using Fisher information and show that its complexity scales linearly with the dataset size. Our experiments on SVHN, CIFAR-10/100, and ImageNet classification show up to 9.3% improvement for biased datasets with label noise compared to prior methods and, importantly, up to 36.6% gain for underrepresented SVHN classes.","url_abs":"https://arxiv.org/abs/2103.05863v2","url_pdf":"https://arxiv.org/pdf/2103.05863v2.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":"autodo-robust-autoaugment-for-biased-data","repo_url":"https://github.com/gudovskiy/autodo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.05863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.05863"}},"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":"deterministic:regex_extraction","url":"https://github.com/gudovskiy/autodo","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"2ee8bbf5cc664aa8","entry":"apply_augment","repo":"gudovskiy/autodo","repo_kind":"official","path":"custom_transforms/dada_augment.py","file_url":"https://github.com/gudovskiy/autodo/blob/HEAD/custom_transforms/dada_augment.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":"2ee8bbf5cc664aa8"}},{"code_sha256_prefix":"2503981c085add0b","entry":"dada_reduced_cifar100","repo":"gudovskiy/autodo","repo_kind":"official","path":"custom_transforms/dada_augment.py","file_url":"https://github.com/gudovskiy/autodo/blob/HEAD/custom_transforms/dada_augment.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":"2503981c085add0b"}},{"code_sha256_prefix":"fa81fe1d347ec7e7","entry":"dada_reduced_svhn","repo":"gudovskiy/autodo","repo_kind":"official","path":"custom_transforms/dada_augment.py","file_url":"https://github.com/gudovskiy/autodo/blob/HEAD/custom_transforms/dada_augment.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":"fa81fe1d347ec7e7"}},{"code_sha256_prefix":"e23610775abae63b","entry":"dada_resnet50_rimagenet","repo":"gudovskiy/autodo","repo_kind":"official","path":"custom_transforms/dada_augment.py","file_url":"https://github.com/gudovskiy/autodo/blob/HEAD/custom_transforms/dada_augment.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":"e23610775abae63b"}},{"code_sha256_prefix":"0e01d35d9ddb931b","entry":"get_augment","repo":"gudovskiy/autodo","repo_kind":"official","path":"custom_transforms/dada_augment.py","file_url":"https://github.com/gudovskiy/autodo/blob/HEAD/custom_transforms/dada_augment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e01d35d9ddb931b"}},{"code_sha256_prefix":"1e0e3c15411377ed","entry":"DadaAugment","repo":"gudovskiy/autodo","repo_kind":"official","path":"custom_transforms/dada_augment.py","file_url":"https://github.com/gudovskiy/autodo/blob/HEAD/custom_transforms/dada_augment.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":"1e0e3c15411377ed"}},{"code_sha256_prefix":"e8d4871b0093493a","entry":"dada_reduced_cifar10","repo":"gudovskiy/autodo","repo_kind":"official","path":"custom_transforms/dada_augment.py","file_url":"https://github.com/gudovskiy/autodo/blob/HEAD/custom_transforms/dada_augment.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":"e8d4871b0093493a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}