{"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/regularizing-deep-networks-with-semantic-data","title":"Regularizing Deep Networks with Semantic Data Augmentation","arxiv_id":"2007.10538","date":"2020-07-21","proceeding":null,"authors":["Yulin Wang","Gao Huang","Shiji Song","Xuran Pan","Yitong Xia","Cheng Wu"],"abstract":"Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and class-agnostic operations, leading to limited diversity for augmented samples. To this end, we propose a novel semantic data augmentation algorithm to complement traditional approaches. The proposed method is inspired by the intriguing property that deep networks are effective in learning linearized features, i.e., certain directions in the deep feature space correspond to meaningful semantic transformations, e.g., changing the background or view angle of an object. Based on this observation, translating training samples along many such directions in the feature space can effectively augment the dataset for more diversity. To implement this idea, we first introduce a sampling based method to obtain semantically meaningful directions efficiently. Then, an upper bound of the expected cross-entropy (CE) loss on the augmented training set is derived by assuming the number of augmented samples goes to infinity, yielding a highly efficient algorithm. In fact, we show that the proposed implicit semantic data augmentation (ISDA) algorithm amounts to minimizing a novel robust CE loss, which adds minimal extra computational cost to a normal training procedure. In addition to supervised learning, ISDA can be applied to semi-supervised learning tasks under the consistency regularization framework, where ISDA amounts to minimizing the upper bound of the expected KL-divergence between the augmented features and the original features. Although being simple, ISDA consistently improves the generalization performance of popular deep models (e.g., ResNets and DenseNets) on a variety of datasets, i.e., CIFAR-10, CIFAR-100, SVHN, ImageNet, and Cityscapes.","url_abs":"https://arxiv.org/abs/2007.10538v5","url_pdf":"https://arxiv.org/pdf/2007.10538v5.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":"regularizing-deep-networks-with-semantic-data","repo_url":"https://github.com/blackfeather-wang/ISDA-for-Deep-Networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2007.10538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10538"}},"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/blackfeather-wang/ISDA-for-Deep-Networks","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/blackfeatherwang/ISDA-for-Deep-Networks","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/speedinghzl/pytorch-segmentation-toolbox","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"ran_honours":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"found_in_text":{"samples":4,"ran":3,"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":2,"samples":[{"code_sha256_prefix":"422a78ccd75601b6","entry":"EstimatorCV","repo":"blackfeather-wang/ISDA-for-Deep-Networks","repo_kind":"official","path":"Image classification on CIFAR/ISDA.py","file_url":"https://github.com/blackfeather-wang/ISDA-for-Deep-Networks/blob/HEAD/Image%20classification%20on%20CIFAR/ISDA.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":"422a78ccd75601b6"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"speedinghzl/pytorch-segmentation-toolbox","repo_kind":"found_in_text","path":"networks/deeplabv3.py","file_url":"https://github.com/speedinghzl/pytorch-segmentation-toolbox/blob/HEAD/networks/deeplabv3.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"26664d79586aad5a","entry":"get_palette","repo":"speedinghzl/pytorch-segmentation-toolbox","repo_kind":"found_in_text","path":"evaluate.py","file_url":"https://github.com/speedinghzl/pytorch-segmentation-toolbox/blob/HEAD/evaluate.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26664d79586aad5a"}},{"code_sha256_prefix":"6ec02fe7ffee8530","entry":"pad_image","repo":"speedinghzl/pytorch-segmentation-toolbox","repo_kind":"found_in_text","path":"evaluate.py","file_url":"https://github.com/speedinghzl/pytorch-segmentation-toolbox/blob/HEAD/evaluate.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ec02fe7ffee8530"}},{"code_sha256_prefix":"9f0d35073e5bc8f5","entry":"ISDALoss","repo":"blackfeather-wang/ISDA-for-Deep-Networks","repo_kind":"official","path":"Image classification on CIFAR/ISDA.py","file_url":"https://github.com/blackfeather-wang/ISDA-for-Deep-Networks/blob/HEAD/Image%20classification%20on%20CIFAR/ISDA.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":"9f0d35073e5bc8f5"}},{"code_sha256_prefix":"9dace7a45606441d","entry":"predict_sliding","repo":"speedinghzl/pytorch-segmentation-toolbox","repo_kind":"found_in_text","path":"evaluate.py","file_url":"https://github.com/speedinghzl/pytorch-segmentation-toolbox/blob/HEAD/evaluate.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":"9dace7a45606441d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}