{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:42:03Z","timestamp":1760600523193,"version":"build-2065373602"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11704-024-40632-2","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:58:31Z","timestamp":1760597911000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating scale imbalance and conflicting gradients in deep multi-task learning"],"prefix":"10.1007","volume":"20","author":[{"given":"Yuepeng","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhao","family":"Gou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuehao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"40632_CR1","doi-asserted-by":"publisher","first-page":"e00321","DOI":"10.1016\/j.btre.2019.e00321","volume":"22","author":"A Buetti-Dinh","year":"2019","unstructured":"Buetti-Dinh A, Galli V, Bellenberg S, Ilie O, Herold M, Christel S, Boretska M, Pivkin I V, Wilmes P, Sand W, Vera M, Dopson M. Deep neural networks outperform human expert\u2019s capacity in characterizing bioleaching bacterial biofilm composition. Biotechnology Reports, 2019, 22: e00321","journal-title":"Biotechnology Reports"},{"issue":"9","key":"40632_CR2","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1109\/TPAMI.2007.1107","volume":"29","author":"A J O\u2019Toole","year":"2007","unstructured":"O\u2019Toole A J, Phillips P J, Jiang F, Ayyad J, Penard N, Abdi H. Face recognition algorithms surpass humans matching faces over changes in illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(9): 1642\u20131646","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"40632_CR3","doi-asserted-by":"publisher","first-page":"1871","DOI":"10.1109\/CVPR.2019.00197","volume-title":"Proceedings of 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"S K Liu","year":"2019","unstructured":"Liu S K, Johns E, Davison A J. End-to-end multi-task learning with attention. In: Proceedings of 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019, 1871\u20131880"},{"key":"40632_CR4","first-page":"5381","volume-title":"Proceedings of 2021 IEEE\/CVF International Conference on Computer Vision","author":"Z Dai","year":"2021","unstructured":"Dai Z, Jiang Y, Li Y, Liu B, Chan A B, Vasconcelos N. BEV-Net: assessing social distancing compliance by joint people localization and geometric reasoning. In: Proceedings of 2021 IEEE\/CVF International Conference on Computer Vision. 2021, 5381\u20135391"},{"issue":"12","key":"40632_CR5","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1145\/3663363","volume":"56","author":"S Chen","year":"2024","unstructured":"Chen S, Zhang Y, Yang Q. Multi-task learning in natural language processing: an overview. ACM Computing Surveys, 2024, 56(12): 295","journal-title":"ACM Computing Surveys"},{"issue":"12","key":"40632_CR6","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","volume":"34","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Yang Q. A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(12): 5586\u20135609","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"7","key":"40632_CR7","first-page":"3614","volume":"44","author":"S Vandenhende","year":"2022","unstructured":"Vandenhende S, Georgoulis S, Van Gansbeke W, Proesmans M, Dai D, Van Gool L. Multi-task learning for dense prediction tasks: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(7): 3614\u20133633","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"40632_CR8","unstructured":"Ruder S. An overview of multi-task learning in deep neural networks. 2017, arXiv preprint arXiv: 1706.05098"},{"key":"40632_CR9","first-page":"489","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"T Yu","year":"2020","unstructured":"Yu T, Kumar S, Gupta A, Levine S, Hausman K, Finn C. Gradient surgery for multi-task learning. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 489"},{"key":"40632_CR10","first-page":"794","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Z Chen","year":"2018","unstructured":"Chen Z, Badrinarayanan V, Lee C-Y, Rabinovich A. GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks. In: Proceedings of the 35th International Conference on Machine Learning. 2018, 794\u2013803"},{"key":"40632_CR11","first-page":"1013","volume-title":"Proceedings of 2018 IEEE Intelligent Vehicles Symposium","author":"M Teichmann","year":"2018","unstructured":"Teichmann M, Weber M, Z\u00f6llner J, Cipolla R, Urtasun R. MultiNet: Real-time joint semantic reasoning for autonomous driving. In: Proceedings of 2018 IEEE Intelligent Vehicles Symposium. 2018, 1013\u20131020"},{"key":"40632_CR12","doi-asserted-by":"publisher","first-page":"3994","DOI":"10.1109\/CVPR.2016.433","volume-title":"Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"I Misra","year":"2016","unstructured":"Misra I, Shrivastava A, Gupta A, Hebert M. Cross-stitch networks for multi-task learning. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, 3994\u20134003"},{"key":"40632_CR13","doi-asserted-by":"publisher","first-page":"7482","DOI":"10.1109\/CVPR.2018.00781","volume-title":"Proceedings of 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"R Cipolla","year":"2018","unstructured":"Cipolla R, Gal Y, Kendall A. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2018, 7482\u20137491"},{"key":"40632_CR14","first-page":"9977","volume-title":"Proceedings of the 33rd AAAI Conference on Artificial Intelligence","author":"S Liu","year":"2019","unstructured":"Liu S, Liang Y, Gitter A. Loss-balanced task weighting to reduce negative transfer in multi-task learning. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. 2019, 9977\u20139978"},{"key":"40632_CR15","first-page":"1","volume-title":"Proceedings of the 23rd IEEE International Conference on Intelligent Transportation Systems","author":"I Leang","year":"2020","unstructured":"Leang I, Sistu G, B\u00fcrger F, Bursuc A, Yogamani S K. Dynamic task weighting methods for multi-task networks in autonomous driving systems. In: Proceedings of the 23rd IEEE International Conference on Intelligent Transportation Systems. 2020, 1\u20138"},{"key":"40632_CR16","first-page":"1","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"Z Wang","year":"2021","unstructured":"Wang Z, Tsvetkov Y, Firat O, Cao Y. Gradient vaccine: investigating and improving multi-task optimization in massively multilingual models. In: Proceedings of the 9th International Conference on Learning Representations. 2021, 1\u201322"},{"key":"40632_CR17","doi-asserted-by":"publisher","first-page":"3213","DOI":"10.1109\/CVPR.2016.350","volume-title":"Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M Cordts","year":"2016","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B. The cityscapes dataset for semantic urban scene understanding. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016, 3213\u20133223"},{"key":"40632_CR18","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Proceedings of the 12th European Conference on Computer Vision-ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman N, Hoiem D, Kohli P, Fergus R. Indoor segmentation and support inference from RGBD images. In: Proceedings of the 12th European Conference on Computer Vision-ECCV 2012. 2012, 746\u2013760"},{"issue":"2","key":"40632_CR19","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams C K I, Winn J, Zisserman A. The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 2010, 88(2): 303\u2013338","journal-title":"International Journal of Computer Vision"},{"key":"40632_CR20","first-page":"1851","volume-title":"Proceedings of 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K K Maninis","year":"2019","unstructured":"Maninis K K, Radosavovic I, Kokkinos I. Attentive single-tasking of multiple tasks. In: Proceedings of 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019, 1851\u20131860"},{"issue":"12","key":"40632_CR21","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R. SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481\u20132495","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"40632_CR22","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Proceedings of the 15th European Conference on Computer Vision-ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen L-C, Zhu Y, Papandreou G, Schroff F, Adam H. Encoderdecoder with Atrous separable convolution for semantic image segmentation. In: Proceedings of the 15th European Conference on Computer Vision-ECCV 2018. 2018, 833\u2013851"},{"key":"40632_CR23","first-page":"2650","volume-title":"Proceedings of 2015 IEEE International Conference on Computer Vision","author":"D Eigen","year":"2015","unstructured":"Eigen D, Fergus R. Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of 2015 IEEE International Conference on Computer Vision. 2015, 2650\u20132658"},{"key":"40632_CR24","first-page":"13","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"D P Kingma","year":"2014","unstructured":"Kingma D P, Ba J. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations. 2014, 13"},{"key":"40632_CR25","unstructured":"Chen L-C, Papandreou G, Schroff F, Adam H. Rethinking atrous convolution for semantic image segmentation. 2017, arXiv preprint arXiv: 1706.05587"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-40632-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-024-40632-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-024-40632-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:58:35Z","timestamp":1760597915000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-024-40632-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":25,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["40632"],"URL":"https:\/\/doi.org\/10.1007\/s11704-024-40632-2","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"25 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests or financial conflicts to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2002318"}}