{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:10Z","timestamp":1735198810263,"version":"3.32.0"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802512","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"11558-11565","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics"],"prefix":"10.1109","author":[{"given":"Elena","family":"Camuffo","sequence":"first","affiliation":[{"name":"Samsung R&D Institute UK (SRUK),United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umberto","family":"Michieli","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute UK (SRUK),United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone","family":"Milani","sequence":"additional","affiliation":[{"name":"University of Padova,Padova,Italy,35129"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jijoong","family":"Moon","sequence":"additional","affiliation":[{"name":"Samsung Research Korea, Seoul R&D Campus,Seoul,Rep. of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mete","family":"Ozay","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute UK (SRUK),United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"ICML","author":"Recht","key":"ref2"},{"article-title":"Ultralytics yolov8","year":"2023","author":"Jocher","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345152"},{"article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"ICLR","author":"Hendrycks","key":"ref6"},{"article-title":"Explaining and harnessing adversarial examples","volume-title":"ICLR","author":"Goodfellow","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341474"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3647623"},{"key":"ref12","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2020","journal-title":"ArXiv:1907.07484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00747"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3045882"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01560"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196887"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00526"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00051"},{"article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"ICLR","author":"Hendrycks","key":"ref21"},{"article-title":"NOTE: Robust continual test-time adaptation against temporal correlation","volume-title":"NeurIPS","author":"Gong","key":"ref22"},{"article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"ICLR","author":"Wang","key":"ref23"},{"article-title":"Towards stable test-time adaptation in dynamic wild world","volume-title":"ICLR","author":"Niu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341653"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.08.031"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342254"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01628"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_4"},{"key":"ref31","article-title":"Improving robustness without sacrificing accuracy with patch gaussian augmentation","author":"Lopes","year":"2019","journal-title":"ArXiv:1906.02611"},{"article-title":"Augmax: Adversarial composition of random augmentations for robust training","volume-title":"NeurIPS","author":"Wang","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447639"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00816"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561808"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160773"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341345"},{"article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"ICML","author":"Lee","key":"ref38"},{"article-title":"Memo: Test time robustness via adaptation and augmentation","volume-title":"NeurIPS","author":"Zhang","key":"ref39"},{"article-title":"SITA: Single Image Test-time Adaptation","volume-title":"CVPR","author":"Khurana","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00243"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"article-title":"Efficient test-time model adaptation without forgetting","volume-title":"ICML","author":"Niu","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593862"},{"key":"ref45","article-title":"Evaluating prediction-time batch normalization for robustness under covariate shift","author":"Nado","year":"2020","journal-title":"ArXiv:2006.10963"},{"article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"NeurIPS","author":"Schneider","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00361"},{"article-title":"Improved deep metric learning with multi-class n-pair loss objective","volume-title":"NeurIPS","author":"Sohn","key":"ref48"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref49"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","year":"2015","author":"Ioffe","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5244\/c.30.87"},{"key":"ref54","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW50498.2020.00203","article-title":"Cspnet: A new backbone that can enhance learning capability of cnn","volume-title":"CVPRW","author":"Wang"},{"article-title":"DeepLab2: A TensorFlow Library for Deep Labeling","year":"2021","author":"Weber","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"article-title":"Making convolutional networks shift-invariant again","volume-title":"ICML","author":"Zhang","key":"ref59"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"year":"2016","key":"ref61","article-title":"Torchvision: Pytorch\u2019s computer vision library"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00370"},{"article-title":"Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs","volume-title":"CVPR","author":"Sun","key":"ref63"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802512.pdf?arnumber=10802512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:23Z","timestamp":1735196483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802512","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}