{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:01:28Z","timestamp":1752192088878,"version":"3.41.2"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0112100"],"award-info":[{"award-number":["2021ZD0112100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018526","name":"Postdoctoral Fellowship Program of CPSF","doi-asserted-by":"publisher","award":["GZC20233458"],"award-info":[{"award-number":["GZC20233458"]}],"id":[{"id":"10.13039\/501100018526","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3462788","type":"journal-article","created":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T15:27:09Z","timestamp":1727278029000},"page":"12091-12105","source":"Crossref","is-referenced-by-count":0,"title":["Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multitask Learning Perspective"],"prefix":"10.1109","volume":"36","author":[{"given":"Yuanze","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun-Mei","family":"Feng","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Fusionopolis, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3765-9787","authenticated-orcid":false,"given":"Qilong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5324-3642","authenticated-orcid":false,"given":"Guanglei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859706"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3307126"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3350335"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2469286"},{"key":"ref7","first-page":"1","article-title":"Learning multiple tasks with multilinear relationship networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Long"},{"key":"ref8","article-title":"Uni-perceiver V2: A generalist model for large-scale vision and vision-language tasks","author":"Li","year":"2022","journal-title":"arXiv:2211.09808"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref10","article-title":"Auxiliary tasks in multi-task learning","author":"Liebel","year":"2018","journal-title":"arXiv:1805.06334"},{"key":"ref11","first-page":"9120","article-title":"Which tasks should be learned together in multi-task learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Standley"},{"key":"ref12","first-page":"1","article-title":"Adaptive auxiliary task weighting for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lin"},{"key":"ref13","article-title":"Adapting auxiliary losses using gradient similarity","author":"Du","year":"2018","journal-title":"arXiv:1812.02224"},{"key":"ref14","article-title":"Auto-lambda: Disentangling dynamic task relationships","author":"Liu","year":"2022","journal-title":"arXiv:2202.03091"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3234166"},{"key":"ref20","article-title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning","author":"Lin","year":"2021","journal-title":"arXiv:2111.10603"},{"article-title":"Towards impartial multi-task learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3270878"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3319546"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109587","article-title":"Task weighting based on particle filter in deep multi-task learning with a view to uncertainty and performance","volume":"140","author":"Aghajanzadeh","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3225179"},{"key":"ref27","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref28","article-title":"Multi-task learning as multi-objective optimization","author":"Sener","year":"2018","journal-title":"arXiv:1810.04650"},{"key":"ref29","first-page":"12060","article-title":"Pareto multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lin"},{"key":"ref30","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref31","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref32","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref36","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2104.10858"},{"key":"ref41","article-title":"Composite learning for robust and effective dense predictions","author":"Kanakis","year":"2022","journal-title":"arXiv:2210.07239"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref42"},{"key":"ref43","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10693501.pdf?arnumber=10693501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:20:13Z","timestamp":1752103213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10693501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":43,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3462788","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}