{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:20:08Z","timestamp":1773804008561,"version":"3.50.1"},"reference-count":232,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/jproc.2024.3435012","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:51:15Z","timestamp":1723053075000},"page":"516-543","source":"Crossref","is-referenced-by-count":16,"title":["When Multitask Learning Meets Partial Supervision: A Computer Vision Review"],"prefix":"10.1109","volume":"112","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9121-5216","authenticated-orcid":false,"given":"Maxime","family":"Fontana","sequence":"first","affiliation":[{"name":"Department of Informatics, King’s College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9531-2813","authenticated-orcid":false,"given":"Michael","family":"Spratling","sequence":"additional","affiliation":[{"name":"Department of Informatics, King’s College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4933-0073","authenticated-orcid":false,"given":"Miaojing","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering and Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Efficient adaptive ensembling for image classification","author":"Bruno","year":"2022","journal-title":"arXiv:2206.07394"},{"key":"ref2","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref3","first-page":"4700","article-title":"Densely connected convolutional networks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Huang"},{"key":"ref4","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref5","article-title":"InternImage: Exploring large-scale vision foundation models with deformable convolutions","author":"Wang","year":"2022","journal-title":"arXiv:2211.05778"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"USB: Universal-scale object detection benchmark","author":"Shinya","year":"2021","journal-title":"arXiv:2103.14027"},{"key":"ref10","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref12","article-title":"Visualizing and understanding convolutional networks","author":"Zeiler","year":"2013","journal-title":"arXiv:1311.2901"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref14","first-page":"1817","article-title":"A framework for learning predictive structures from multiple tasks and unlabeled data","volume":"6","author":"Ando","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2026"},{"key":"ref16","article-title":"Partly supervised multitask learning","author":"Imran","year":"2020","journal-title":"arXiv:2005.02523"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01831"},{"key":"ref18","article-title":"Semi-supervised multi-task learning for semantics and depth","author":"Wang","year":"2021","journal-title":"arXiv:2110.07197"},{"key":"ref19","first-page":"1","article-title":"Semi-supervised multitask learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8512294"},{"key":"ref21","article-title":"MultiNet: Multi-modal multi-task learning for autonomous driving","author":"Chowdhuri","year":"2017","journal-title":"arXiv:1709.05581"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00325"},{"key":"ref23","article-title":"Effective adaptation in multi-task co-training for unified autonomous driving","author":"Liang","year":"2022","journal-title":"arXiv:2209.08953"},{"key":"ref24","article-title":"Multi-task learning in the wilderness","volume-title":"Proc. ICML","author":"Karpathy"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9196905"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101837"},{"key":"ref27","article-title":"Dynamic multi-task learning for face recognition with facial expression","author":"Ming","year":"2019","journal-title":"arXiv:1911.03281"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00112"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00720"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1049\/htl.2019.0066"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2021.614277"},{"issue":"1","key":"ref33","doi-asserted-by":"crossref","first-page":"283","DOI":"10.3390\/s22010283","article-title":"Multi-task model for esophageal lesion analysis using endoscopic images: Classification with image retrieval and segmentation with attention","volume":"22","author":"Yu","year":"2021","journal-title":"Sensors"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/CinC53138.2021.9662869"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref36","first-page":"1","article-title":"Conditionally adaptive multi-task learning: Improving transfer learning in NLP using fewer parameters & less data","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Pilault"},{"key":"ref37","first-page":"148","article-title":"A multi-task approach for named entity recognition in social media data","volume-title":"Proc. 3rd Workshop Noisy User-Generated Text","author":"Aguilar"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-demos.1"},{"key":"ref39","first-page":"2965","article-title":"Multi-task learning for sequence tagging: An empirical study","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Changpinyo"},{"key":"ref40","article-title":"Improving part-of-speech tagging via multi-task learning and character-level word representations","author":"Anastasyev","year":"2018","journal-title":"arXiv:1807.00818"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3570640"},{"key":"ref42","first-page":"269","article-title":"Multi-task learning for recommender system","volume-title":"Proc. 2nd Asian Conf. Mach. Learn.","volume":"13","author":"Ning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/296"},{"key":"ref44","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"arXiv:1706.05098"},{"key":"ref45","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020","journal-title":"arXiv:2009.09796"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3054719"},{"issue":"9","key":"ref48","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.3390\/electronics9091363","article-title":"A survey of multi-task deep reinforcement learning","volume":"9","author":"Vithayathil Varghese","year":"2020","journal-title":"Electronics"},{"key":"ref49","article-title":"A survey of multi-task learning in natural language processing: Regarding task relatedness and training methods","author":"Zhang","year":"2022","journal-title":"arXiv:2204.03508"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3663363"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943604"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref53","article-title":"Factors of influence for transfer learning across diverse appearance domains and task types","author":"Mensink","year":"2021","journal-title":"arXiv:2103.13318"},{"key":"ref54","first-page":"1","article-title":"Multi-task feature learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"19","author":"Argyriou"},{"issue":"21","key":"ref55","first-page":"615","article-title":"Learning multiple tasks with kernel methods","volume":"6","author":"Evgeniou","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","article-title":"Taking advantage of sparsity in multi-task learning","author":"Lounici","year":"2009","journal-title":"arXiv:0903.1468"},{"key":"ref57","article-title":"Multi-task feature learning via efficient \u21132,1-norm minimization","author":"Liu","year":"2012","journal-title":"arXiv:1205.2631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553434"},{"key":"ref59","first-page":"1","article-title":"A dirty model for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Jalali"},{"key":"ref60","article-title":"Learning task grouping and overlap in multi-task learning","author":"Kumar","year":"2012","journal-title":"arXiv:1206.6417"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_10"},{"issue":"2","key":"ref62","first-page":"35","article-title":"Multi-task learning for classification with Dirichlet process priors","volume":"8","author":"Xue","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","article-title":"Clustered multi-task learning: A convex formulation","author":"Jacob","year":"2008","journal-title":"arXiv:0809.2085"},{"key":"ref64","first-page":"1","article-title":"Kernels for multi\u2013task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"17","author":"Micchelli"},{"issue":"1","key":"ref65","first-page":"368","article-title":"Learning a kernel for multi-task clustering","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"25","author":"Gu"},{"key":"ref66","first-page":"1","article-title":"Clustered multi-task learning via alternating structure optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Zhou"},{"key":"ref67","article-title":"UberNet: Training a \u2018universal\u2019 convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory","author":"Kokkinos","year":"2016","journal-title":"arXiv:1609.02132"},{"key":"ref68","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"Kendall","year":"2017","journal-title":"arXiv:1705.07115"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00116"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01557"},{"key":"ref74","article-title":"InvPT: Inverted pyramid multi-task transformer for dense scene understanding","author":"Ye","year":"2022","journal-title":"arXiv:2203.07997"},{"key":"ref75","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"ref77","article-title":"NDDR-CNN: Layerwise feature fusing in multi-task CNNs by neural discriminative dimensionality reduction","author":"Gao","year":"2018","journal-title":"arXiv:1801.08297"},{"key":"ref78","article-title":"Network in network","author":"Lin","year":"2013","journal-title":"arXiv:1312.4400"},{"key":"ref79","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref83","article-title":"Focal self-attention for local\u2013global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"arXiv:2107.00641"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref85","article-title":"MulT: An end-to-end multitask learning transformer","author":"Bhattacharjee","year":"2022","journal-title":"arXiv:2205.08303"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_18"},{"key":"ref87","article-title":"Deep multi-task representation learning: A tensor factorisation approach","author":"Yang","year":"2016","journal-title":"arXiv:1605.06391"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1980.1102314"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"ref90","article-title":"Trace norm regularised deep multi-task learning","author":"Yang","year":"2016","journal-title":"arXiv:1606.04038"},{"key":"ref91","article-title":"Policy distillation","author":"Rusu","year":"2015","journal-title":"arXiv:1511.06295"},{"key":"ref92","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"Parisotto","year":"2015","journal-title":"arXiv:1511.06342"},{"key":"ref93","article-title":"Distral: Robust multitask reinforcement learning","author":"Whye Teh","year":"2017","journal-title":"arXiv:1707.04175"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_13"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_5"},{"key":"ref97","first-page":"1","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Rebuffi"},{"key":"ref98","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00847"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00195"},{"key":"ref102","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2017","journal-title":"arXiv:1709.01507"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref104","article-title":"BERT and PALs: Projected attention layers for efficient adaptation in multi-task learning","author":"Cooper Stickland","year":"2019","journal-title":"arXiv:1902.02671"},{"key":"ref105","article-title":"Beyond shared hierarchies: Deep multitask learning through soft layer ordering","author":"Meyerson","year":"2017","journal-title":"arXiv:1711.00108"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref107","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv:1701.06538"},{"key":"ref108","article-title":"DSelect-k: Differentiable selection in the mixture of experts with applications to multi-task learning","author":"Hazimeh","year":"2021","journal-title":"arXiv:2106.03760"},{"key":"ref109","article-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017","journal-title":"arXiv:1701.08734"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205489"},{"key":"ref111","article-title":"An evolutionary approach to dynamic introduction of tasks in large-scale multitask learning systems","author":"Gesmundo","year":"2022","journal-title":"arXiv:2205.12755"},{"key":"ref112","article-title":"Flexible multi-task networks by learning parameter allocation","author":"Maziarz","year":"2019","journal-title":"arXiv:1910.04915"},{"key":"ref113","article-title":"AdaShare: Learning what to share for efficient deep multi-task learning","author":"Sun","year":"2019","journal-title":"arXiv:1911.12423"},{"key":"ref114","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref115","article-title":"AutoMTL: A programming framework for automating efficient multi-task learning","author":"Zhang","year":"2021","journal-title":"arXiv:2110.13076"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00147"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref118","article-title":"Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification","author":"Lu","year":"2016","journal-title":"arXiv:1611.05377"},{"key":"ref119","article-title":"Branched multi-task networks: Deciding what layers to share","author":"Vandenhende","year":"2019","journal-title":"arXiv:1904.02920"},{"key":"ref120","article-title":"Toward edge-efficient dense predictions with synergistic multi-task neural architecture search","author":"Vu","year":"2022","journal-title":"arXiv:2210.01384"},{"key":"ref121","article-title":"A comprehensive survey on hardware-aware neural architecture search","author":"Benmeziane","year":"2021","journal-title":"arXiv:2101.09336"},{"key":"ref122","article-title":"Learning anytime predictions in neural networks via adaptive loss balancing","author":"Hu","year":"2017","journal-title":"arXiv:1708.06832"},{"key":"ref123","article-title":"Auxiliary tasks in multi-task learning","author":"Liebel","year":"2018","journal-title":"arXiv:1805.06334"},{"key":"ref124","article-title":"Towards impartial multi-task learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref125","article-title":"MultiNe++: Multi-stream feature aggregation and geometric loss strategy for multi-task learning","author":"Chennupati","year":"2019","journal-title":"arXiv:1904.08492"},{"key":"ref126","article-title":"End-to-end multi-task learning with attention","author":"Liu","year":"2018","journal-title":"arXiv:1803.10704"},{"key":"ref127","article-title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning","author":"Lin","year":"2021","journal-title":"arXiv:2111.10603"},{"key":"ref128","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","author":"Chen","year":"2017","journal-title":"arXiv:1711.02257"},{"key":"ref129","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","author":"Chen","year":"2020","journal-title":"arXiv:2010.06808"},{"key":"ref130","article-title":"Adapting auxiliary losses using gradient similarity","author":"Du","year":"2018","journal-title":"arXiv:1812.02224"},{"key":"ref131","article-title":"Regularizing deep multi-task networks using orthogonal gradients","author":"Suteu","year":"2019","journal-title":"arXiv:1912.06844"},{"key":"ref132","article-title":"Gradient surgery for multi-task learning","author":"Yu","year":"2020","journal-title":"arXiv:2001.06782"},{"key":"ref133","first-page":"1","article-title":"Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref134","article-title":"RotoGrad: Gradient homogenization in multitask learning","author":"Javaloy","year":"2021","journal-title":"arXiv:2103.02631"},{"key":"ref135","article-title":"Controllable Pareto multi-task learning","author":"Lin","year":"2020","journal-title":"arXiv:2010.06313"},{"key":"ref136","article-title":"Learning the Pareto front with hypernetworks","author":"Navon","year":"2021","journal-title":"arXiv:2010.04104"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/j.crma.2012.03.014"},{"key":"ref138","article-title":"Multi-task learning as multi-objective optimization","author":"Sener","year":"2018","journal-title":"arXiv:1810.04650"},{"key":"ref139","first-page":"427","article-title":"Revisiting frank-wolfe: Projection-free sparse convex optimization","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","volume":"28","author":"Jaggi"},{"key":"ref140","article-title":"Conflict-averse gradient descent for multi-task learning","author":"Liu","year":"2021","journal-title":"arXiv:2110.14048"},{"key":"ref141","article-title":"Pareto multi-task learning","author":"Lin","year":"2019","journal-title":"arXiv:1912.12854"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2013.2281533"},{"key":"ref143","article-title":"Efficient continuous Pareto exploration in multi-task learning","author":"Ma","year":"2020","journal-title":"arXiv:2006.16434"},{"key":"ref144","article-title":"HyperNetworks","author":"Ha","year":"2016","journal-title":"arXiv:1609.09106"},{"key":"ref145","first-page":"15895","article-title":"A multi-objective\/multi-task learning framework induced by Pareto stationarity","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Momma"},{"key":"ref146","article-title":"Multi-task learning as a bargaining game","author":"Navon","year":"2022","journal-title":"arXiv:2202.01017"},{"issue":"1","key":"ref147","doi-asserted-by":"crossref","first-page":"128","DOI":"10.2307\/1906951","article-title":"Two-person cooperative games","volume":"21","author":"Nash","year":"1953","journal-title":"Econometrica"},{"key":"ref148","first-page":"1","article-title":"Do current multi-task optimization methods in deep learning even help?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xin"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"ref150","article-title":"12-in-1: Multi-task vision and language representation learning","author":"Lu","year":"2019","journal-title":"arXiv:1912.02315"},{"key":"ref151","article-title":"Self-paced multi-task learning","author":"Li","year":"2016","journal-title":"arXiv:1604.01474"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref154","article-title":"Learning to multi-task by active sampling","author":"Sharma","year":"2017","journal-title":"arXiv:1702.06053"},{"key":"ref155","first-page":"521","article-title":"Learning with whom to share in multi-task feature learning","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML)","author":"Kang"},{"key":"ref156","first-page":"1593","article-title":"Learning multiple tasks with multilinear relationship networks","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Long"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/2538028"},{"key":"ref158","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.jmva.2011.05.015","article-title":"The multilinear normal distribution: Introduction and some basic properties","volume":"113","author":"Ohlson","year":"2013","journal-title":"J. Multivariate Anal."},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01267"},{"key":"ref160","article-title":"Which tasks should be learned together in multi-task learning?","author":"Standley","year":"2019","journal-title":"arXiv:1905.07553"},{"key":"ref161","article-title":"Efficiently identifying task groupings for multi-task learning","author":"Fifty","year":"2021","journal-title":"arXiv:2109.04617"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref165","article-title":"Discriminative unsupervised feature learning with exemplar convolutional neural networks","author":"Dosovitskiy","year":"2014","journal-title":"arXiv:1406.6909"},{"key":"ref166","article-title":"Learning features by watching objects move","author":"Pathak","year":"2016","journal-title":"arXiv:1612.06370"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00512"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486472"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.56"},{"key":"ref172","article-title":"GPU-accelerated real-time stixel computation","author":"Hernandez-Juarez","year":"2016","journal-title":"arXiv:1610.04124"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00091"},{"key":"ref175","article-title":"Anomaly detection in video via self-supervised and multi-task learning","author":"Georgescu","year":"2020","journal-title":"arXiv:2011.07491"},{"key":"ref176","article-title":"SSMTL++: Revisiting self-supervised multi-task learning for video anomaly detection","author":"Barbalau","year":"2022","journal-title":"arXiv:2207.08003"},{"key":"ref177","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"arXiv:1908.02265"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01421"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref180","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021","journal-title":"arXiv:2111.06377"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1405.0312"},{"issue":"21","key":"ref184","doi-asserted-by":"crossref","first-page":"3538","DOI":"10.3390\/electronics11213538","article-title":"A multi-task dense network with self-supervised learning for retinal vessel segmentation","volume":"11","author":"Tu","year":"2022","journal-title":"Electronics"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_15"},{"key":"ref186","article-title":"An evaluation of self-supervised pre-training for skin-lesion analysis","author":"Chaves","year":"2021","journal-title":"arXiv:2106.09229"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414405"},{"key":"ref188","first-page":"29","article-title":"LingJing at SemEval-2022 task 1: Multi-task self-supervised pre-training for multilingual reverse dictionary","volume-title":"Proc. 16th Int. Workshop Semantic Eval.","author":"Li"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2009.66"},{"key":"ref190","article-title":"Self-supervised relative depth learning for urban scene understanding","author":"Jiang","year":"2017","journal-title":"arXiv:1712.04850"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_35"},{"key":"ref192","first-page":"1","article-title":"Boosting semantic segmentation with multi-task self-supervised learning for autonomous driving applications","volume-title":"Proc. NIPS","author":"Novosel"},{"key":"ref193","article-title":"Three ways to improve semantic segmentation with self-supervised depth estimation","author":"Hoyer","year":"2020","journal-title":"arXiv:2012.10782"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref195","article-title":"ClassMix: Segmentation-based data augmentation for semi-supervised learning","author":"Olsson","year":"2020","journal-title":"arXiv:2007.07936"},{"key":"ref196","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"Tarvainen","year":"2017","journal-title":"arXiv:1703.01780"},{"key":"ref197","article-title":"Improving semi-supervised and domain-adaptive semantic segmentation with self-supervised depth estimation","author":"Hoyer","year":"2021","journal-title":"arXiv:2108.12545"},{"key":"ref198","article-title":"Multi-task self-supervised learning for image segmentation task","author":"Gao","year":"2023","journal-title":"arXiv:2302.02483"},{"key":"ref199","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"arXiv:1406.2661"},{"key":"ref200","article-title":"Adversarial feature learning","author":"Donahue","year":"2016","journal-title":"arXiv:1605.09782"},{"key":"ref201","article-title":"Adversarial learning for semi-supervised semantic segmentation","author":"Hung","year":"2018","journal-title":"arXiv:1802.07934"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190911"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref204","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2019","journal-title":"arXiv:1911.05722"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref206","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv:2002.05709"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00690"},{"key":"ref209","article-title":"Multi-layer feature aggregation for deep scene parsing models","author":"Yu","year":"2020","journal-title":"arXiv:2011.02572"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00584"},{"key":"ref211","first-page":"10106","article-title":"UniDepth: Universal monocular metric depth estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Piccinelli"},{"key":"ref212","first-page":"10371","article-title":"Depth anything: Unleashing the power of large-scale unlabeled data","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yang"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00501"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01289"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02057"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00457"},{"key":"ref217","first-page":"1","article-title":"Taskprompter: Spatial-channel multi-task prompting for dense scene understanding","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Ye"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25411"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/AIID51893.2021.9456562"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01121"},{"key":"ref222","article-title":"FiLM: Visual reasoning with a general conditioning layer","author":"Perez","year":"2017","journal-title":"arXiv:1709.07871"},{"key":"ref223","article-title":"The natural language decathlon: Multitask learning as question answering","author":"McCann","year":"2018","journal-title":"arXiv:1806.08730"},{"key":"ref224","article-title":"Improving few-shot learning with auxiliary self-supervised pretext tasks","author":"Simard","year":"2021","journal-title":"arXiv:2101.09825"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref226","first-page":"1","article-title":"Universal few-shot learning of dense prediction tasks with visual token matching","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_28"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139439"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2015.38"},{"key":"ref231","article-title":"Minimalist and high-performance semantic segmentation with plain vision transformers","author":"Hong","year":"2023","journal-title":"arXiv:2310.12755"},{"key":"ref232","article-title":"LibMTL: A Python library for multi-task learning","author":"Lin","year":"2022","journal-title":"arXiv:2203.14338"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5\/10654605\/10628096.pdf?arnumber=10628096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T10:27:36Z","timestamp":1725013656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10628096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":232,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2024.3435012","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}