{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T21:31:26Z","timestamp":1773869486190,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3477533","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T17:25:48Z","timestamp":1728581148000},"page":"149593-149605","source":"Crossref","is-referenced-by-count":3,"title":["Dynamic Test-Time Augmentation via Differentiable Functions"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7450-3311","authenticated-orcid":false,"given":"Shohei","family":"Enomoto","sequence":"first","affiliation":[{"name":"NTT, Musashino, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0728-6905","authenticated-orcid":false,"given":"Monikka","family":"Roslianna Busto","sequence":"additional","affiliation":[{"name":"NTT, Musashino, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeharu","family":"Eda","sequence":"additional","affiliation":[{"name":"NTT, Musashino, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Mean embeddings with test-time data augmentation for ensembling of representations","author":"Ashukha","year":"2021","journal-title":"arXiv:2106.08038"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00245"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3446918"},{"key":"ref4","article-title":"EntProp: High entropy propagation for improving accuracy and robustness","volume-title":"Proc. Conf. Uncertainty Artif. Intell. (UAI)","author":"Enomoto"},{"key":"ref5","first-page":"4033","article-title":"NoisyMix: Boosting model robustness to common corruptions","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","volume":"238","author":"Erichson"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01134"},{"key":"ref7","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Geirhos"},{"key":"ref8","article-title":"In search of lost domain generalization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gulrajani"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref12","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hendrycks"},{"key":"ref13","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hendrycks"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01628"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3089598"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803787"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref19","first-page":"63660","article-title":"IPMix: Label-preserving data augmentation method for training robust classifiers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Huang"},{"key":"ref20","first-page":"4163","article-title":"Learning loss for test-time augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Kim"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92185-9_46"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref24","article-title":"Test-time mixup augmentation for uncertainty estimation in skin lesion diagnosis","volume-title":"Proc. Med. Imag. Deep Learn. (MIDL)","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561076"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref27","article-title":"Shape-texture debiased neural network training","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref28","first-page":"580","article-title":"DADA: Differentiable automatic data augmentation","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/117"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568501"},{"key":"ref31","first-page":"1308","article-title":"Greedy policy search: A simple baseline for learnable test-time augmentation","volume-title":"Proc. Conf. Uncertainty Artif. Intell. (UAI)","author":"Lyzhov"},{"key":"ref32","first-page":"1","article-title":"Fast AdvProp","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Mei"},{"key":"ref33","first-page":"3571","article-title":"On interaction between augmentations and corruptions in natural corruption robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Mintun"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-13940-7_1"},{"key":"ref35","first-page":"1","article-title":"Mixup inference: Better exploiting mixup to defend adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Pang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_42"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2950923"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00015"},{"key":"ref39","first-page":"980","article-title":"Global filter networks for image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Rao"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093363"},{"key":"ref41","first-page":"35672","article-title":"Deep invariant networks with differentiable augmentation layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Rommel"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00125"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00424"},{"key":"ref46","first-page":"1","article-title":"Fourier-based augmentations for improved robustness and uncertainty calibration","volume-title":"Proc. Workshop Distrib. Shifts, Connecting Methods Appl. (DistShift)","author":"Soklaski"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_43"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00055"},{"key":"ref50","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"key":"ref51","first-page":"24261","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Tolstikhin"},{"key":"ref52","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Touvron"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191763"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01682"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01036"},{"key":"ref56","first-page":"237","article-title":"AugMax: Adversarial composition of random augmentations for robust training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref57","article-title":"Caltech-UCSD birds 200","author":"Welinder","year":"2010"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219907"},{"key":"ref60","article-title":"A Fourier perspective on model robustness in computer vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yin"},{"key":"ref61","first-page":"1","article-title":"MixProp: Towards high-performance image recognition via dual batch normalisation","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Zhang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01672-y"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10713305.pdf?arnumber=10713305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:42:04Z","timestamp":1732668124000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10713305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3477533","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}