{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:58:05Z","timestamp":1780934285948,"version":"3.54.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114031","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T16:11:56Z","timestamp":1779466316000},"page":"114031","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Adaptively sampling-reusing-mixing decomposed gradients to speed up sharpness aware minimization"],"prefix":"10.1016","volume":"180","author":[{"given":"Jiaxin","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8153-7229","authenticated-orcid":false,"given":"Junbiao","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baochang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114031_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111822","article-title":"SRML: Structure-relation mutual learning network for few-shot image classification","volume":"168","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114031_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111425","article-title":"FSENet: Feature suppression and enhancement network for tiny object detection","volume":"162","author":"Hu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114031_b3","unstructured":"Y. Jiang, B. Neyshabur, H. Mobahi, D. Krishnan, S. Bengio, Fantastic generalization measures and where to find them, in: Proceedings of the International Conference on Learning Representations, ICLR, 2020, pp. 2821\u20132854."},{"key":"10.1016\/j.patcog.2026.114031_b4","first-page":"11648","article-title":"Exploring the vulnerability of deep neural networks: A study of parameter corruption","volume":"vol. 35","author":"Sun","year":"2021"},{"key":"10.1016\/j.patcog.2026.114031_b5","unstructured":"P. Foret, A. Kleiner, H. Mobahi, B. Neyshabur, Sharpness-aware minimization for efficiently improving generalization, in: Proceedings of the International Conference on Learning Representations, ICLR, 2021, pp. 1\u201312."},{"key":"10.1016\/j.patcog.2026.114031_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110496","article-title":"Boosting sharpness-aware training with dynamic neighborhood","volume":"153","author":"Chen","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114031_b7","unstructured":"J. Zhuang, B. Gong, L. Yuan, Y. Cui, H. Adam, N. Dvornek, S. Tatikonda, J. Duncan, T. Liu, Surrogate gap minimization improves sharpness-aware training, in: Proceedings of the International Conference on Learning Representations, ICLR, 2022, pp. 1\u201324."},{"issue":"16","key":"10.1016\/j.patcog.2026.114031_b8","doi-asserted-by":"crossref","first-page":"2877","DOI":"10.3390\/rs16162877","article-title":"Implicit sharpness-aware minimization for domain generalization","volume":"16","author":"Dong","year":"2024","journal-title":"Remote. Sens."},{"key":"10.1016\/j.patcog.2026.114031_b9","doi-asserted-by":"crossref","first-page":"23439","DOI":"10.52202\/068431-1703","article-title":"Sharpness-aware training for free","volume":"35","author":"Du","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"10.1016\/j.patcog.2026.114031_b10","unstructured":"J. Du, H. Yan, J. Feng, J.T. Zhou, L. Zhen, R.S.M. Goh, V.Y. Tan, Efficient sharpness-aware minimization for improved training of neural networks, in: Proceedings of the International Conference on Learning Representations, ICLR, 2022, pp. 1\u201314."},{"key":"10.1016\/j.patcog.2026.114031_b11","first-page":"16208","article-title":"Asymptotic unbiased sample sampling to speed up sharpness-aware minimization","volume":"vol. 39","author":"Deng","year":"2025"},{"key":"10.1016\/j.patcog.2026.114031_b12","doi-asserted-by":"crossref","unstructured":"Y. Liu, S. Mai, X. Chen, C.-J. Hsieh, Y. You, Towards efficient and scalable sharpness-aware minimization, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 12360\u201312370.","DOI":"10.1109\/CVPR52688.2022.01204"},{"key":"10.1016\/j.patcog.2026.114031_b13","unstructured":"W. Jiang, H. Yang, Y. Zhang, J. Kwok, An Adaptive Policy to Employ Sharpness-Aware Minimization, in: Proceedings of the International Conference on Learning Representations, ICLR, 2023, pp. 1\u201319."},{"key":"10.1016\/j.patcog.2026.114031_b14","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"26982","article-title":"Penalizing gradient norm for efficiently improving generalization in deep learning","author":"Zhao","year":"2022"},{"key":"10.1016\/j.patcog.2026.114031_b15","doi-asserted-by":"crossref","unstructured":"T. Li, P. Zhou, Z. He, X. Cheng, X. Huang, Friendly sharpness-aware minimization, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 5631\u20135640.","DOI":"10.1109\/CVPR52733.2024.00538"},{"key":"10.1016\/j.patcog.2026.114031_b16","unstructured":"N.S. Keskar, D. Mudigere, J. Nocedal, M. Smelyanskiy, P.T.P. Tang, On large-batch training for deep learning: Generalization gap and sharp minima, in: Proceedings of the International Conference on Learning Representations, ICLR, 2017, pp. 2874\u20132890."},{"key":"10.1016\/j.patcog.2026.114031_b17","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","author":"Andriushchenko","year":"2022"},{"key":"10.1016\/j.patcog.2026.114031_b18","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.patcog.2026.114031_b19","series-title":"Tiny imagenet visual recognition challenge","first-page":"3","author":"Le","year":"2015"},{"key":"10.1016\/j.patcog.2026.114031_b20","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2026.114031_b21","series-title":"Wide residual networks","author":"Zagoruyko","year":"2016"},{"key":"10.1016\/j.patcog.2026.114031_b22","doi-asserted-by":"crossref","unstructured":"D. Han, J. Kim, J. Kim, Deep pyramidal residual networks, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 5927\u20135935.","DOI":"10.1109\/CVPR.2017.668"},{"key":"10.1016\/j.patcog.2026.114031_b23","series-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"10.1016\/j.patcog.2026.114031_b24","series-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"10.1016\/j.patcog.2026.114031_b25","series-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"10.1016\/j.patcog.2026.114031_b26","doi-asserted-by":"crossref","unstructured":"X. Zhang, R. Xu, H. Yu, H. Zou, P. Cui, Gradient norm aware minimization seeks first-order flatness and improves generalization, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 20247\u201320257.","DOI":"10.1109\/CVPR52729.2023.01939"},{"key":"10.1016\/j.patcog.2026.114031_b27","doi-asserted-by":"crossref","unstructured":"J. Huang, L. Qu, R. Jia, B. Zhao, O2u-net: A simple noisy label detection approach for deep neural networks, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2019, pp. 3326\u20133334.","DOI":"10.1109\/ICCV.2019.00342"},{"key":"10.1016\/j.patcog.2026.114031_b28","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114031_b29","doi-asserted-by":"crossref","unstructured":"H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 2881\u20132890.","DOI":"10.1109\/CVPR.2017.660"},{"key":"10.1016\/j.patcog.2026.114031_b30","doi-asserted-by":"crossref","unstructured":"L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"10.1016\/j.patcog.2026.114031_b31","series-title":"Proceedings of the International Conference on Computer Vision","first-page":"991","article-title":"Semantic contours from inverse detectors","author":"Hariharan","year":"2011"},{"key":"10.1016\/j.patcog.2026.114031_b32","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"89","article-title":"Simcc: A simple coordinate classification perspective for human pose estimation","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.114031_b33","doi-asserted-by":"crossref","unstructured":"M. Andriluka, L. Pishchulin, P. Gehler, B. Schiele, 2D Human Pose Estimation: New Benchmark and State of the Art Analysis, in: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2014, pp. 3686\u20133693.","DOI":"10.1109\/CVPR.2014.471"},{"key":"10.1016\/j.patcog.2026.114031_b34","doi-asserted-by":"crossref","unstructured":"S. Xie, R. Girshick, P. Doll\u00e1r, Z. Tu, K. He, Aggregated residual transformations for deep neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, pp. 1492\u20131500.","DOI":"10.1109\/CVPR.2017.634"},{"key":"10.1016\/j.patcog.2026.114031_b35","doi-asserted-by":"crossref","unstructured":"J. Li, S. Bian, A. Zeng, C. Wang, B. Pang, W. Liu, C. Lu, Human pose regression with residual log-likelihood estimation, in: Proceedings of the International Conference on Computer Vision, ICCV, 2021, pp. 11025\u201311034.","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"10.1016\/j.patcog.2026.114031_b36","series-title":"OpenMMLab pose estimation toolbox and benchmark","author":"MMPose Contributors","year":"2020"},{"key":"10.1016\/j.patcog.2026.114031_b37","unstructured":"S.K. Esser, J.L. McKinstry, D. Bablani, R. Appuswamy, D.S. Modha, Learned Step Size Quantization, in: Proceedings of the International Conference on Learning Representations, ICLR, 2020, pp. 6910\u20136922."},{"key":"10.1016\/j.patcog.2026.114031_b38","unstructured":"X. Wei, R. Gong, Y. Li, X. Liu, F. Yu, QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization, in: Proceedings of the International Conference on Learning Representations, ICLR, 2021, pp. 1\u201319."},{"key":"10.1016\/j.patcog.2026.114031_b39","doi-asserted-by":"crossref","unstructured":"B. Jacob, S. Kligys, B. Chen, M. Zhu, M. Tang, A. Howard, H. Adam, D. Kalenichenko, Quantization and training of neural networks for efficient integer-arithmetic-only inference, in: Proceedings of the Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 2704\u20132713.","DOI":"10.1109\/CVPR.2018.00286"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009969?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326009969?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T15:04:55Z","timestamp":1780931095000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326009969"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":39,"alternative-id":["S0031320326009969"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114031","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptively sampling-reusing-mixing decomposed gradients to speed up sharpness aware minimization","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114031","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114031"}}