{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:41:37Z","timestamp":1765309297080,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754907","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"151-160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EBaR: Efficient Buffer and Resetting for Single-Sample Continual Test-Time Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6397-4184","authenticated-orcid":false,"given":"Tianyi","family":"Ma","sequence":"first","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0990-5506","authenticated-orcid":false,"given":"Maoying","family":"Qiao","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 3080--3090","author":"Bartler Alexander","year":"2022","unstructured":"Alexander Bartler, Andre B\u00fchler, Felix Wiewel, Mario D\u00f6bler, and Bin Yang. 2022. Mt3: Meta test-time training for self-supervised test-time adaption. In International Conference on Artificial Intelligence and Statistics. PMLR, 3080--3090."},{"key":"e_1_3_2_1_2_1","volume-title":"Adamatch: A unified approach to semi-supervised learning and domain adaptation. arXiv preprint arXiv:2106.04732","author":"Berthelot David","year":"2021","unstructured":"David Berthelot, Rebecca Roelofs, Kihyuk Sohn, Nicholas Carlini, and Alex Kurakin. 2021. Adamatch: A unified approach to semi-supervised learning and domain adaptation. arXiv preprint arXiv:2106.04732 (2021)."},{"key":"e_1_3_2_1_3_1","volume-title":"SANTA: Source Anchoring Network and Target Alignment for Continual Test Time Adaptation. Transactions on Machine Learning Research","author":"Chakrabarty Goirik","year":"2023","unstructured":"Goirik Chakrabarty, Manogna Sreenivas, and Soma Biswas. 2023. SANTA: Source Anchoring Network and Target Alignment for Continual Test Time Adaptation. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"e_1_3_2_1_5_1","volume-title":"When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations. arXiv preprint arXiv:2106.01548","author":"Chen Xiangning","year":"2021","unstructured":"Xiangning Chen, Cho-Jui Hsieh, and Boqing Gong. 2021. When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations. arXiv preprint arXiv:2106.01548 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00744"},{"key":"e_1_3_2_1_8_1","volume-title":"et al","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al . 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25922"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01134"},{"key":"e_1_3_2_1_11_1","volume-title":"DALSA: Domain adaptation for supervised learning from sparsely annotated MR images","author":"Goetz Michael","year":"2015","unstructured":"Michael Goetz, Christian Weber, Franciszek Binczyk, Joanna Polanska, Rafal Tarnawski, Barbara Bobek-Billewicz, Ullrich Koethe, Jens Kleesiek, Bram Stieltjes, and Klaus H Maier-Hein. 2015. DALSA: Domain adaptation for supervised learning from sparsely annotated MR images. IEEE transactions on medical imaging 35, 1 (2015), 184--196."},{"key":"e_1_3_2_1_12_1","first-page":"27253","article-title":"NOTE: Robust continual test-time adaptation against temporal correlation","volume":"35","author":"Gong Taesik","year":"2022","unstructured":"Taesik Gong, Jongheon Jeong, Taewon Kim, Yewon Kim, Jinwoo Shin, and Sung-Ju Lee. 2022. NOTE: Robust continual test-time adaptation against temporal correlation. Advances in Neural Information Processing Systems 35 (2022), 27253--27266.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25160"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks and Thomas Dietterich. 2019. Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. Proceedings of the International Conference on Learning Representations (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"Test-time adaptation via self-training with nearest neighbor information. arXiv preprint arXiv:2207.10792","author":"Jang Minguk","year":"2022","unstructured":"Minguk Jang, Sae-Young Chung, and Hye Won Chung. 2022. Test-time adaptation via self-training with nearest neighbor information. arXiv preprint arXiv:2207.10792 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00354-022-00197-9"},{"key":"e_1_3_2_1_20_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.167"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02181-w"},{"key":"e_1_3_2_1_23_1","first-page":"60791","article-title":"Generalized semi-supervised learning via self-supervised feature adaptation","volume":"36","author":"Liang Jiachen","year":"2023","unstructured":"Jiachen Liang, Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, and Xilin Chen. 2023. Generalized semi-supervised learning via self-supervised feature adaptation. Advances in Neural Information Processing Systems 36 (2023), 60791--60803.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02707"},{"key":"e_1_3_2_1_25_1","volume-title":"Vida: Homeostatic visual domain adapter for continual test time adaptation. arXiv preprint arXiv:2306.04344","author":"Liu Jiaming","year":"2023","unstructured":"Jiaming Liu, Senqiao Yang, Peidong Jia, Renrui Zhang, Ming Lu, Yandong Guo, Wei Xue, and Shanghang Zhang. 2023. Vida: Homeostatic visual domain adapter for continual test time adaptation. arXiv preprint arXiv:2306.04344 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02237"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01892"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00254"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01435"},{"key":"e_1_3_2_1_31_1","volume-title":"Test-time adaptation to distribution shift by confidence maximization and input transformation. arXiv preprint arXiv:2106.14999","author":"Mummadi Chaithanya Kumar","year":"2021","unstructured":"Chaithanya Kumar Mummadi, Robin Hutmacher, Kilian Rambach, Evgeny Levinkov, Thomas Brox, and Jan Hendrik Metzen. 2021. Test-time adaptation to distribution shift by confidence maximization and input transformation. arXiv preprint arXiv:2106.14999 (2021)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00209"},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 16888--16905","author":"Niu Shuaicheng","year":"2022","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Yaofo Chen, Shijian Zheng, Peilin Zhao, and Mingkui Tan. 2022. Efficient test-time model adaptation without forgetting. In International conference on machine learning. PMLR, 16888--16905."},{"key":"e_1_3_2_1_34_1","volume-title":"Towards stable test-time adaptation in dynamic wild world. arXiv preprint arXiv:2302.12400","author":"Niu Shuaicheng","year":"2023","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, and Mingkui Tan. 2023. Towards stable test-time adaptation in dynamic wild world. arXiv preprint arXiv:2302.12400 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"e_1_3_2_1_36_1","first-page":"39915","article-title":"Rdumb: A simple approach that questions our progress in continual test-time adaptation","volume":"36","author":"Press Ori","year":"2023","unstructured":"Ori Press, Steffen Schneider, Matthias K\u00fcmmerer, and Matthias Bethge. 2023. Rdumb: A simple approach that questions our progress in continual test-time adaptation. Advances in Neural Information Processing Systems 36 (2023), 39915--39935.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","volume-title":"Adaptive wavelet-VNet for single-sample test time adaptation in medical image segmentation. Medical physics 51, 12","author":"Qian Xiaoxue","year":"2024","unstructured":"Xiaoxue Qian, Weiguo Lu, and You Zhang. 2024. Adaptive wavelet-VNet for single-sample test time adaptation in medical image segmentation. Medical physics 51, 12 (2024), 8865--8881."},{"key":"e_1_3_2_1_38_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arXiv:2103.00020 [cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_39_1","volume-title":"ICML 2022 Shift Happens Workshop.","author":"Rusak Evgenia","year":"2022","unstructured":"Evgenia Rusak, Steffen Schneider, Peter Vincent Gehler, Oliver Bringmann, Wieland Brendel, and Matthias Bethge. 2022. ImageNet-D: A new challenging robustness dataset inspired by domain adaptation. In ICML 2022 Shift Happens Workshop."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00206"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00374"},{"key":"e_1_3_2_1_42_1","volume-title":"So Kweon, and Sungha Choi.","author":"Song Junha","year":"2023","unstructured":"Junha Song, Jungsoo Lee, In So Kweon, and Sungha Choi. 2023. EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11920--11929."},{"key":"e_1_3_2_1_43_1","volume-title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers. arXiv preprint arXiv:2106.10270","author":"Steiner Andreas","year":"2021","unstructured":"Andreas Steiner, Alexander Kolesnikov, Xiaohua Zhai, Ross Wightman, Jakob Uszkoreit, and Lucas Beyer. 2021. How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers. arXiv preprint arXiv:2106.10270 (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"MLP-Mixer: An all-MLP Architecture for Vision. arXiv preprint arXiv:2105.01601","author":"Tolstikhin Ilya","year":"2021","unstructured":"Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, and Alexey Dosovitskiy. 2021. MLP-Mixer: An all-MLP Architecture for Vision. arXiv preprint arXiv:2105.01601 (2021)."},{"key":"e_1_3_2_1_45_1","volume-title":"Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726","author":"Wang Dequan","year":"2020","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2020. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00172"},{"key":"e_1_3_2_1_48_1","unstructured":"Zixin Wang Yadan Luo Liang Zheng Zhuoxiao Chen Sen Wang and Zi Huang. 2024. In search of lost online test-time adaptation: A survey. International Journal of Computer Vision (2024) 1--34."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02240"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01528"},{"key":"e_1_3_2_1_52_1","volume-title":"Wide residual networks. arXiv preprint arXiv:1605.07146","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)."},{"key":"e_1_3_2_1_53_1","volume-title":"LiT: Zero-Shot Transfer with Locked-image Text Tuning. CVPR","author":"Zhai Xiaohua","year":"2022","unstructured":"Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, and Lucas Beyer. 2022. LiT: Zero-Shot Transfer with Locked-image Text Tuning. CVPR (2022)."},{"volume-title":"Semi-supervised adapted hmms for unusual event detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05)","author":"Zhang Dong","key":"e_1_3_2_1_54_1","unstructured":"Dong Zhang, Daniel Gatica-Perez, Samy Bengio, and Iain McCowan. 2005. Semi-supervised adapted hmms for unusual event detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), Vol. 1. IEEE, 611--618."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01739"},{"key":"e_1_3_2_1_56_1","volume-title":"A Fully Test-Time Training Framework for Semi-Supervised Node Classification on Out-of-Distribution Graphs. ACM Transactions on Knowledge Discovery from Data 18, 7","author":"Zhang Jiaxin","year":"2024","unstructured":"Jiaxin Zhang, Yiqi Wang, Xihong Yang, and En Zhu. 2024. A Fully Test-Time Training Framework for Semi-Supervised Node Classification on Out-of-Distribution Graphs. ACM Transactions on Knowledge Discovery from Data 18, 7 (2024), 1--19."},{"key":"e_1_3_2_1_57_1","first-page":"38629","article-title":"Memo: Test time robustness via adaptation and augmentation","volume":"35","author":"Zhang Marvin","year":"2022","unstructured":"Marvin Zhang, Sergey Levine, and Chelsea Finn. 2022. Memo: Test time robustness via adaptation and augmentation. Advances in Neural Information Processing Systems 35 (2022), 38629--38642.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_58_1","volume-title":"International Conference on Machine Learning. PMLR, 41647--41676","author":"Zhang Yifan","year":"2023","unstructured":"Yifan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, and Tieniu Tan. 2023. Adanpc: Exploring non-parametric classifier for test-time adaptation. In International Conference on Machine Learning. PMLR, 41647--41676."},{"key":"e_1_3_2_1_59_1","volume-title":"Surrogate Gap Minimization Improves Sharpness-Aware Training. ICLR","author":"Zhuang Juntang","year":"2022","unstructured":"Juntang Zhuang, Boqing Gong, Liangzhe Yuan, Yin Cui, Hartwig Adam, Nicha Dvornek, Sekhar Tatikonda, James Duncan, and Ting Liu. 2022. Surrogate Gap Minimization Improves Sharpness-Aware Training. ICLR (2022)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:38:59Z","timestamp":1765309139000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754907"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":59,"alternative-id":["10.1145\/3746027.3754907","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754907","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}