{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:38:24Z","timestamp":1783575504775,"version":"3.55.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007105","name":"Universit\u00e4t Mannheim","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007105","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Multi-task learning (MTL) enables a single neural network to solve multiple tasks simultaneously, offering efficiency and improved generalization potential through shared representations. A central challenge in MTL is balancing task-specific losses during training to avoid performance degradation. While uncertainty-based loss weighting (UW) is a popular and competitive approach, we argue that it suffers from several limitations, including overfitting, rigid homoscedastic assumptions, and a lack of theoretical grounding for various loss functions. Therefore, we propose\n                    <jats:italic>Soft Optimal Uncertainty Weighting<\/jats:italic>\n                    (UW-SO), a novel loss weighting method that builds on UW by deriving analytically optimal weights and applying softmax normalization with adaptable temperature parameter, thereby alleviating several of the shortcomings of UW. Through extensive experiments across diverse datasets and architectures, we show that UW-SO achieves superior and robust performance compared to a variety of existing loss weighting methods. Additionally, we provide insights into the effects of temperature selection and propose measures to reduce computational demand.\n                  <\/jats:p>","DOI":"10.1007\/s11263-025-02625-x","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T17:46:05Z","timestamp":1766511965000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Investigating Uncertainty Weighting for Multi-Task Learning: Insights and Analytical Alternative"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4713-9328","authenticated-orcid":false,"given":"Lukas","family":"Kirchdorfer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Sesterhenn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Bartelt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heiner","family":"Stuckenschmidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lukas","family":"Schott","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan M.","family":"K\u00f6hler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"2625_CR1","doi-asserted-by":"crossref","unstructured":"Badrinarayanan, V., Kendall, A. & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 39(12), pp. 2481\u20132495. IEEE.","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"2625_CR2","unstructured":"Baijiong, L., Feiyang, Y. & Z.\u00a0Yu. (2021). A closer look at loss weighting in multi-task learning. ArXiv preprint arXiv: abs\/2111.10603 ."},{"key":"2625_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R. & J.\u00a0Weston (2009). Curriculum learning. In Proceedings of the 26th annual international conference on machine learning, pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"},{"key":"2625_CR4","unstructured":"Caccia, M., Caccia, L., Fedus, W., Larochelle, H., Pineau, J., & Charlin, L. (2019). Language gans falling short."},{"issue":"1","key":"2625_CR5","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R. (1997). Multitask learning. Machine learning, 28(1), 41\u201375.","journal-title":"Multitask learning. Machine learning"},{"key":"2625_CR6","unstructured":"Chang, J., Zhang, X., Guo, Y., Meng, G., Xiang, S. & Pan, C. (2019). Differentiable architecture search with ensemble gumbel-softmax. arXiv preprint arXiv:1905.01786 ."},{"key":"2625_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F. & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2625_CR8","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C., & Rabinovich, A. (2018). Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In J.\u00a0G. Dy and A.\u00a0Krause (Eds.), Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018, Volume\u00a080 of Proceedings of Machine Learning Research, pp. 793\u2013802. PMLR."},{"key":"2625_CR9","unstructured":"Chen, Z., Ngiam, J., Huang, Y., Luong, T., Kretzschmar, H., Chai, Y., & Anguelov, D. (2020). Just pick a sign: Optimizing deep multitask models with gradient sign dropout. In H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.\u00a0Balcan, and H.\u00a0Lin (Eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual."},{"key":"2625_CR10","doi-asserted-by":"crossref","unstructured":"Chennupati, S., Sistu, G., Yogamani, S., & A\u00a0Rawashdeh, S. (2019). Multinet++: Multi-stream feature aggregation and geometric loss strategy for multi-task learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 0\u20130.","DOI":"10.1109\/CVPRW.2019.00159"},{"key":"2625_CR11","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S. & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp. 3213\u20133223. IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.350"},{"key":"2625_CR12","doi-asserted-by":"crossref","unstructured":"Duong, L., Cohn, T., Bird, S., & Cook, P. (2015). Low resource dependency parsing: Cross-lingual parameter sharing in a neural network parser. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), Beijing, China, pp. 845\u2013850. Association for Computational Linguistics.","DOI":"10.3115\/v1\/P15-2139"},{"key":"2625_CR13","unstructured":"Elich, C., Kirchdorfer, L., Koehler, J.M. & Schott, L. (2024). Examining common paradigms in multi-task learning. In Pattern Recognition - 46th DAGM German Conference, DAGM GCPR 2024, Munich, Germany, September 10-13, 2024, Proceedings, Volume 15297 of Lecture Notes in Computer Science. Springer."},{"key":"2625_CR14","series-title":"Lecture Notes in Computer Science","first-page":"523","volume-title":"Computer Vision - ACCV 2022\u201316th Asian Conference on Computer Vision, Macao, China, December 4\u20138, 2022, Proceedings, Part I","author":"C Fan","year":"2022","unstructured":"Fan, C., Chen, W., Tian, J., Li, Y., He, H., & Jin, Y. (2022). Maxgnr: A dynamic weight strategy via maximizing gradient-to-noise ratio for multi-task learning. Lecture Notes in Computer ScienceIn L. Wang, J. Gall, T. Chin, I. Sato, & R. Chellappa (Eds.), Computer Vision - ACCV 2022\u201316th Asian Conference on Computer Vision, Macao, China, December 4\u20138, 2022, Proceedings, Part I (Vol. 13841, pp. 523\u2013538). Springer."},{"key":"2625_CR15","first-page":"27503","volume":"34","author":"C Fifty","year":"2021","unstructured":"Fifty, C., Amid, E., Zhao, Z., Yu, T., Anil, R., & Finn, C. (2021). Efficiently identifying task groupings for multi-task learning. Advances in Neural Information Processing Systems, 34, 27503\u201327516.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2625_CR16","unstructured":"Guo, C., Pleiss, G., Sun, Y. & Weinberger, K.Q. (2017). On calibration of modern neural networks. In International conference on machine learning, pp. 1321\u20131330. PMLR."},{"key":"2625_CR17","doi-asserted-by":"crossref","unstructured":"Guo, M., Haque, A., Huang, D.A., Yeung, S., & Fei-Fei, L. (2018). Dynamic task prioritization for multitask learning. In Proceedings of the European Conference on Computer Vision (ECCV).","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"2625_CR18","doi-asserted-by":"crossref","unstructured":"Heuer, F., Mantowsky, S., Bukhari, S.S. & Schneider, G. (2021). Multitask-centernet (MCN): efficient and diverse multitask learning using an anchor free approach. In IEEE\/CVF International Conference on Computer Vision Workshops, ICCVW 2021, Montreal, BC, Canada, October 11-17, 2021, pp. 997\u20131005. IEEE.","DOI":"10.1109\/ICCVW54120.2021.00116"},{"key":"2625_CR19","unstructured":"Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 ."},{"key":"2625_CR20","doi-asserted-by":"crossref","unstructured":"Hu, R. & Singh, A. (2021). Unit: Multimodal multitask learning with a unified transformer. In 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021, pp. 1419\u20131429. IEEE.","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"2625_CR21","first-page":"48510","volume":"36","author":"Y Hu","year":"2023","unstructured":"Hu, Y., Xian, R., Wu, Q., Fan, Q., Yin, L., & Zhao, H. (2023). Revisiting scalarization in multi-task learning: A theoretical perspective. Advances in Neural Information Processing Systems, 36, 48510\u201348533.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2625_CR22","doi-asserted-by":"crossref","unstructured":"Ishihara, K., Kanervisto, A., Miura, J., & Hautam\u00e4ki, V. (2021). Multi-task learning with attention for end-to-end autonomous driving. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2021, virtual, June 19-25, 2021, pp. 2902\u20132911. Computer Vision Foundation \/ IEEE.","DOI":"10.1109\/CVPRW53098.2021.00325"},{"key":"2625_CR23","unstructured":"Jang, E., Gu, S., & Poole, B. (2016). Categorical reparameterization with gumbel-softmax."},{"key":"2625_CR24","unstructured":"Javaloy, A. & Valera, I. (2022). Rotograd: Gradient homogenization in multitask learning. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net."},{"key":"2625_CR25","unstructured":"Kendall, A. & Gal, Y. (2017). What uncertainties do we need in bayesian deep learning for computer vision? In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 5574\u20135584."},{"key":"2625_CR26","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y. & Cipolla, R. (2018). Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 7482\u20137491. IEEE Computer Society.","DOI":"10.1109\/CVPR.2018.00781"},{"key":"2625_CR27","unstructured":"Kirchdorfer, L., Elich, C., Kutsche, S., Stuckenschmidt, H., Schott, L. & K\u00f6hler, J.M. (2024). Analytical uncertainty-based loss weighting in multi-task learning. In Pattern Recognition - 46th DAGM German Conference, DAGM GCPR 2024, Munich, Germany, September 10-13, 2024, Proceedings, Volume 15297 of Lecture Notes in Computer Science. Springer."},{"key":"2625_CR28","unstructured":"Kurin, V., Palma, A.D., Kostrikov, I., Whiteson, S. & Mudigonda, P.K. (2022). In defense of the unitary scalarization for deep multi-task learning. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, December, virtual."},{"key":"2625_CR29","doi-asserted-by":"crossref","unstructured":"Lakkapragada, A., Sleiman, E., Surabhi, S., & Wall, D. P. (2023). Mitigating negative transfer in multi-task learning with exponential moving average loss weighting strategies (student abstract). In B. Williams, Y. Chen, & J. Neville (Eds.), Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7\u201314, 2023 (pp. 16246\u201316247). AAAI Press.","DOI":"10.1609\/aaai.v37i13.26983"},{"key":"2625_CR30","doi-asserted-by":"crossref","unstructured":"Li, D., Ju, H., Sharma, A. & Zhang, H.R. (2023). Boosting multitask learning on graphs through higher-order task affinities. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1213\u20131222.","DOI":"10.1145\/3580305.3599265"},{"key":"2625_CR31","doi-asserted-by":"crossref","unstructured":"Li, D., A.\u00a0Sharma, & H.R. Zhang (2024). Scalable multitask learning using gradient-based estimation of task affinity. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1542\u20131553.","DOI":"10.1145\/3637528.3671835"},{"key":"2625_CR32","unstructured":"Liang, S., Li, Y., & Srikant, R. (2018). Enhancing the reliability of out-of-distribution image detection in neural networks."},{"key":"2625_CR33","unstructured":"Lin, B., Jiang, W., Ye, F., Zhang, Y., Chen, P., Chen, Y.C., Liu, S. & Kwok, J.T. (2023). Dual-balancing for multi-task learning. arXiv preprint arXiv:2308.12029 ."},{"key":"2625_CR34","unstructured":"Lin, B. & Zhang, Y. (2023). LibMTL: A python library for multi-task learning. Journal of Machine Learning Research ."},{"key":"2625_CR35","unstructured":"Liu, B., Feng, Y., Stone, P. & Liu, Q. (2023). FAMO: fast adaptive multitask optimization. CoRR arXiv: abs\/2306.03792."},{"key":"2625_CR36","unstructured":"Liu, B., Liu, X., Jin, X., Stone, P. & Liu, Q. (2021). Conflict-averse gradient descent for multi-task learning. In M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0N. Dauphin, P.\u00a0Liang, and J.\u00a0W. Vaughan (Eds.), Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pp. 18878\u201318890."},{"key":"2625_CR37","unstructured":"Liu, L., Li, Y., Kuang, Z., Xue, J., Chen, Y., Yang, W., Liao, Q. & Zhang, W. (2021). Towards impartial multi-task learning. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"2625_CR38","doi-asserted-by":"crossref","unstructured":"Liu, S., E.\u00a0Johns, & A.J. Davison (2019). End-to-end multi-task learning with attention. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 1871\u20131880. Computer Vision Foundation \/ IEEE.","DOI":"10.1109\/CVPR.2019.00197"},{"key":"2625_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X. & Tang, X. (2015). Deep learning face attributes in the wild. In 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, December 7-13, 2015, pp. 3730\u20133738. IEEE Computer Society.","DOI":"10.1109\/ICCV.2015.425"},{"key":"2625_CR40","doi-asserted-by":"crossref","unstructured":"Maninis, K., Radosavovic, I. & Kokkinos, I. (2019). Attentive single-tasking of multiple tasks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 1851\u20131860. Computer Vision Foundation \/ IEEE.","DOI":"10.1109\/CVPR.2019.00195"},{"key":"2625_CR41","doi-asserted-by":"crossref","unstructured":"Mao, Y., Wang, Z., Liu, W., Lin, X. & Xie, P. (2022). MetaWeighting: Learning to weight tasks in multi-task learning. In Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, pp. 3436\u20133448. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.findings-acl.271"},{"key":"2625_CR42","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A. & Hebert, M. (2016). Cross-stitch networks for multi-task learning. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp. 3994\u20134003. IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.433"},{"key":"2625_CR43","doi-asserted-by":"crossref","unstructured":"Nathan\u00a0Silberman, Derek\u00a0Hoiem, P.K. & R.\u00a0Fergus (2012). Indoor segmentation and support inference from rgbd images. In Proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"2625_CR44","unstructured":"Navon, A., Shamsian, A., Achituve, I., Maron, H., Kawaguchi, K., Chechik, G. & Fetaya, E. (2022). Multi-task learning as a bargaining game. In K.\u00a0Chaudhuri, S.\u00a0Jegelka, L.\u00a0Song, C.\u00a0Szepesv\u00e1ri, G.\u00a0Niu, and S.\u00a0Sabato (Eds.), International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, Volume 162 of Proceedings of Machine Learning Research, pp. 16428\u201316446. PMLR."},{"key":"2625_CR45","unstructured":"Ruder, S. (2017). An overview of multi-task learning in deep neural networks. ArXiv preprint arXiv:abs\/1706.05098 ."},{"key":"2625_CR46","unstructured":"Sener, O. & Koltun, V. (2018). Multi-task learning as multi-objective optimization. In S.\u00a0Bengio, H.\u00a0M. Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.), Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada, pp. 525\u2013536."},{"key":"2625_CR47","doi-asserted-by":"crossref","unstructured":"Senushkin, D., Patakin, N., Kuznetsov, A. & Konushin, A. (2023). Independent component alignment for multi-task learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20083\u201320093.","DOI":"10.1109\/CVPR52729.2023.01923"},{"key":"2625_CR48","unstructured":"Shi, G., Li, Q., Zhang, W., Chen, J., & Wu, X.M. (2023). Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning. In The Eleventh International Conference on Learning Representations."},{"key":"2625_CR49","unstructured":"Standley, T., Zamir, A., Chen, D., Guibas, L., Malik, J. & Savarese, S. (2020). Which tasks should be learned together in multi-task learning? In International conference on machine learning, pp. 9120\u20139132. PMLR."},{"key":"2625_CR50","first-page":"1988","volume":"2020","author":"Q Tan","year":"2020","unstructured":"Tan, Q., Liu, N., Zhao, X., Yang, H., Zhou, J., & Hu, X. (2020). Learning to hash with graph neural networks for recommender systems. In Proceedings of The Web Conference, 2020, 1988\u20131998.","journal-title":"In Proceedings of The Web Conference"},{"key":"2625_CR51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719","volume-title":"Multi-task learning for dense prediction tasks: A survey","author":"S Vandenhende","year":"2021","unstructured":"Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., & Van Gool, L. (2021). Multi-task learning for dense prediction tasks: A survey. In IEEE transactions on pattern analysis and machine intelligence: IEEE."},{"key":"2625_CR52","unstructured":"Vasu, P.K.A., Saxena, S. & Tuzel, O. (2021). Instance-level task parameters: A robust multi-task weighting framework. arXiv preprint  arXiv:2106.06129 ."},{"key":"2625_CR53","unstructured":"Xin, D., Ghorbani, B., Garg, A., Firat, O., & Gilmer, J. (2022). Do current multi-task optimization methods in deep learning even help? In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, December, virtual."},{"key":"2625_CR54","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X. & Sebe, N. (2018). Pad-net: Multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 675\u2013684. IEEE Computer Society.","DOI":"10.1109\/CVPR.2018.00077"},{"key":"2625_CR55","unstructured":"Yang, Y. & Hospedales, T.M. (2016). Trace norm regularised deep multi-task learning. ArXiv preprint arXiv:abs\/1606.04038 ."},{"key":"2625_CR56","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K. & Finn, C. (2020). Gradient surgery for multi-task learning. In H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.\u00a0Balcan, and H.\u00a0Lin (Eds.), Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02625-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02625-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02625-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T15:38:07Z","timestamp":1771601887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02625-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,23]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2625"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02625-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,23]]},"assertion":[{"value":"31 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"8"}}