{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:29:28Z","timestamp":1777984168382,"version":"3.51.4"},"reference-count":140,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tpami.2023.3330862","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T14:03:56Z","timestamp":1699365836000},"page":"1148-1164","source":"Crossref","is-referenced-by-count":16,"title":["Differentiable Image Data Augmentation and Its Applications: A Survey"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0692-504X","authenticated-orcid":false,"given":"Jian","family":"Shi","sequence":"first","affiliation":[{"name":"Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8636-4264","authenticated-orcid":false,"given":"Hakim","family":"Ghazzai","sequence":"additional","affiliation":[{"name":"Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6701-0639","authenticated-orcid":false,"given":"Yehia","family":"Massoud","sequence":"additional","affiliation":[{"name":"Innovative Technologies Laboratories (ITL), King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1528","article-title":"A kernel theory of modern data augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dao"},{"key":"ref2","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"Perez","year":"2017"},{"key":"ref3","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref6","first-page":"2180","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref7","article-title":"Data augmentation for object detection via differentiable neural rendering","author":"Ning","year":"2021"},{"key":"ref8","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref9","article-title":"MODALS: Modality-agnostic automated data augmentation in the latent space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheung"},{"key":"ref10","article-title":"Negative data augmentation","author":"Sinha","year":"2021"},{"key":"ref11","first-page":"5049","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref12","article-title":"ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring","author":"Berthelot","year":"2019"},{"key":"ref13","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref14","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref16","first-page":"21 271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Grill"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093363"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201383"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.19"},{"key":"ref21","article-title":"GAN augmentation: Augmenting training data using generative adversarial networks","author":"Bowles","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00854"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073592"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925974"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_35"},{"key":"ref27","article-title":"CADDA: Class-wise automatic differentiable data augmentation for EEG signals","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Rommel"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00359"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322996"},{"issue":"1","key":"ref31","first-page":"387","volume-title":"IEEE Robot. Automat. Lett.","volume":"3","author":"Li","year":"2017"},{"key":"ref32","first-page":"8326","article-title":"Radioactive data: Tracing through training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sablayrolles"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-023-01853-2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107791"},{"key":"ref37","first-page":"3528","article-title":"Gradient estimation using stochastic computation graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"Schulman"},{"key":"ref38","first-page":"9609","article-title":"Learning to predict 3D objects with an interpolation-based differentiable renderer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981703"},{"key":"ref41","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"Jaderberg"},{"key":"ref42","article-title":"Differentiable data augmentation with Kornia","author":"Shi","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-89841-w"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-71080-0"},{"key":"ref46","volume-title":"Computer Vision: Algorithms and Applications","author":"Szeliski","year":"2010"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3278287"},{"key":"ref48","first-page":"4177","article-title":"Learning deep embeddings with histogram loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ustinova"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3278287"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10227-z"},{"key":"ref51","article-title":"Data augmentation by pairing samples for images classification","author":"Inoue","year":"2018"},{"key":"ref52","article-title":"YOLOV4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020"},{"key":"ref53","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref55","article-title":"Improving robustness without sacrificing accuracy with patch Gaussian augmentation","author":"Lopes","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00820"},{"key":"ref57","first-page":"4218","article-title":"Improving robustness using generated data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gowal"},{"key":"ref58","article-title":"Synthetic data from diffusion models improves imageNet classification","author":"Azizi","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02064"},{"key":"ref60","article-title":"StableRep: Synthetic images from text-to-image models make strong visual representation learners","author":"Tian","year":"2023"},{"key":"ref61","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"key":"ref62","article-title":"Data augmentation generative adversarial networks","author":"Antoniou","year":"2017"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00935"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00460"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_36"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181070"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/KSE53942.2021.9648720"},{"key":"ref68","article-title":"GAN inversion for data augmentation to improve colonoscopy lesion classification","author":"Golhar","year":"2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_36"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref71","article-title":"LEDITS: Real image editing with DDPM inversion and semantic guidance","author":"Tsaban","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25326"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"ref74","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref75","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref76","first-page":"3358","article-title":"Adversarial training for free!","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shafahi"},{"key":"ref77","article-title":"Improving adversarial robustness requires revisiting misclassified examples","author":"Wang","year":"2019","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00059"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref80","article-title":"Adversarial attacks and defences: A survey","author":"Chakraborty","year":"2018"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108889"},{"key":"ref82","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref83","article-title":"Backpropagation through the void: Optimizing control variates for black-box gradient estimation","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Grathwohl"},{"key":"ref84","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref85","first-page":"3086","article-title":"A-star sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Maddison"},{"key":"ref86","article-title":"Hierarchical multiscale recurrent neural networks","author":"Chung","year":"2016"},{"key":"ref87","article-title":"Understanding straight-through estimator in training activation quantized neural nets","author":"Yin","year":"2019"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_37"},{"key":"ref89","article-title":"Adversarial autoaugment","author":"Zhang","year":"2019"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00668"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref92","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"Maddison","year":"2016"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-f"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.160"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_19"},{"key":"ref97","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78191-0_7"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01063"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00066"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3099858"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.3390\/jmse10070884"},{"key":"ref103","first-page":"12 104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karras"},{"key":"ref104","first-page":"7559","article-title":"Differentiable augmentation for data-efficient GAN training","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049346"},{"key":"ref106","first-page":"12 674","article-title":"Dataset condensation with differentiable siamese augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref107","article-title":"Dissolving is amplifying: Towards fine-grained anomaly detection","author":"Shi","year":"2023"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696121"},{"key":"ref109","first-page":"17 605","article-title":"Learning invariances in neural networks from training data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Benton"},{"key":"ref110","article-title":"Deep invariant networks with differentiable augmentation layers","author":"Rommel","year":"2022"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6051"},{"key":"ref112","first-page":"3239","article-title":"Learning to compose domain-specific transformations for data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ratner"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.18.064076"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref117","first-page":"19 088","article-title":"Improving auto-augment via augmentation-wise weight sharing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-007-0176-2"},{"key":"ref119","first-page":"2731","article-title":"Population based augmentation: Efficient learning of augmentation policy schedules","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ho"},{"key":"ref120","article-title":"Darts: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01200"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00173"},{"key":"ref123","first-page":"6665","article-title":"Fast autoaugment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref124","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref125","article-title":"Deep autoaugmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zheng"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/177"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533048"},{"key":"ref128","article-title":"Instance-specific augmentation: Capturing local invariances","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Miao"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108637"},{"key":"ref130","article-title":"AdaAug: Learning class-and instance-adaptive data augmentation policies","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cheung"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3265266"},{"key":"ref132","article-title":"Stabilizing darts with amended gradient estimation on architectural parameters","author":"Bi","year":"2019"},{"key":"ref133","article-title":"The effects of regularization and data augmentation are class dependent","author":"Balestriero","year":"2022"},{"key":"ref134","first-page":"1310","article-title":"Certified adversarial robustness via randomized smoothing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen"},{"key":"ref135","first-page":"9464","article-title":"Certified adversarial robustness with additive noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref136","article-title":"Mitigating adversarial effects through randomization","author":"Xie","year":"2017"},{"key":"ref137","first-page":"5558","article-title":"White-box vs black-box: Bayes optimal strategies for membership inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sablayrolles"},{"key":"ref138","first-page":"1803","article-title":"A rule for gradient estimator selection, with an application to variational inference","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Geffner"},{"key":"ref139","article-title":"Seeing is not necessarily believing: Limitations of BigGANs for data augmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravuri"},{"key":"ref140","first-page":"10 410","article-title":"On the generalization effects of linear transformations in data augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10384454\/10310260.pdf?arnumber=10310260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:37:55Z","timestamp":1705012675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10310260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":140,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3330862","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.21805797.v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.21805797","asserted-by":"object"}]},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}