{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:19:27Z","timestamp":1778080767613,"version":"3.51.4"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263187","type":"print"},{"value":"9783031263194","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26319-4_31","type":"book-chapter","created":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T06:02:59Z","timestamp":1677823379000},"page":"523-538","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MaxGNR: A Dynamic Weight Strategy via\u00a0Maximizing Gradient-to-Noise Ratio for\u00a0Multi-task Learning"],"prefix":"10.1007","author":[{"given":"Caoyun","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jidong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaohui","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,4]]},"reference":[{"key":"31_CR1","unstructured":"Bottou, L., et al.: Stochastic gradient learning in neural networks. In: NeurIPS (1991)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. Siam Review (2018)","DOI":"10.1137\/16M1080173"},{"key":"31_CR3","volume-title":"Convex Optimization","author":"SP Boyd","year":"2014","unstructured":"Boyd, S.P., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2014)"},{"key":"31_CR4","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.Y., Rabinovich, A.: Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In: ICML (2018)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chennupati, S., Sistu, G., Yogamani, S., Rawashdeh, S.A.: Multinet++: multi-stream feature aggregation and geometric loss strategy for multi-task learning. In: CVPR Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00159"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Cipolla, R., Gal, Y., Kendall, A.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00781"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"31_CR8","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. JMLR 12, 2121\u20132159 (2011)","journal-title":"JMLR"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Gao, Y., Ma, J., Zhao, M., Liu, W., Yuille, A.L.: NDDR-CNN: layerwise feature fusing in multi-task CNNs by neural discriminative dimensionality reduction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00332"},{"key":"31_CR10","volume-title":"Deep Learning","author":"IJ Goodfellow","year":"2016","unstructured":"Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. MIT Press, Adaptive computation and machine learning (2016)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Guo, M., Haque, A., Huang, D.A., Yeung, S., Fei-Fei, L.: Dynamic task prioritization for multitask learning. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"31_CR12","unstructured":"He, F., Liu, T., Tao, D.: Control batch size and learning rate to generalize well: theoretical and empirical evidence. In: NeurIPS (2019)"},{"key":"31_CR13","unstructured":"Hoffer, E., Hubara, I., Soudry, D.: Train longer, generalize better: closing the generalization gap in large batch training of neural networks. In: NeurIPS (2017)"},{"key":"31_CR14","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: generalization gap and sharp minima. In: ICLR (2017)"},{"key":"31_CR15","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"31_CR16","unstructured":"Liu, L., et al.: Towards impartial multi-task learning. In: ICLR (2021)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., Davison, A.J.: End-to-end multi-task learning with attention. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00197"},{"key":"31_CR18","first-page":"1","volume":"18","author":"S Mandt","year":"2017","unstructured":"Mandt, S., Hoffman, M.D., Blei, D.M.: Stochastic gradient descent as approximate bayesian inference. JMLR 18, 1\u201335 (2017)","journal-title":"JMLR"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.433"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Ruder, S., Bingel, J., Augenstein, I., S\u00f8gaard, A.: Latent multi-task architecture learning. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"31_CR21","unstructured":"Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. In: NeurIPS (2018)"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"31_CR23","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: ICML (2013)"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Vandenhende, S., Georgoulis, S., Gansbeke, W.V., Proesmans, M., Dai, D., Gool, L.V.: Multi-task learning for dense prediction tasks: a survey. TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Vandenhende, S., Georgoulis, S., Gool, L.V.: MTI-Net: multi-scale task interaction networks for multi-task learning. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"31_CR26","unstructured":"Wu, J., Hu, W., Xiong, H., Huan, J., Braverman, V., Zhu, Z.: On the noisy gradient descent that generalizes as SGD. In: ICML (2020)"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X., Sebe, N.: Pad-net: Multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00077"},{"key":"31_CR28","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. In: NeurIPS (2020)"},{"key":"31_CR29","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint (2012)"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xiao, L., Wang, Y., Jin, Y.: A generalized recurrent neural architecture for text classification with multi-task learning. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/473"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cui, Z., Xu, C., Jie, Z., Li, X., Yang, J.: Joint task-recursive learning for semantic segmentation and depth estimation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"31_CR32","unstructured":"Zhu, Z., Wu, J., Yu, B., Wu, L., Ma, J.: The anisotropic noise in stochastic gradient descent: its behavior of escaping from sharp minima and regularization effects. In: ICML (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26319-4_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T06:15:31Z","timestamp":1677824131000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26319-4_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263187","9783031263194"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26319-4_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"4 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}