{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:24:43Z","timestamp":1775665483777,"version":"3.50.1"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T00:00:00Z","timestamp":1700265600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1016\/j.neunet.2023.11.038","type":"journal-article","created":{"date-parts":[[2023,11,19]],"date-time":"2023-11-19T17:26:28Z","timestamp":1700414788000},"page":"254-265","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":24,"special_numbering":"C","title":["Multi-Adaptive Optimization for multi-task learning with deep neural networks"],"prefix":"10.1016","volume":"170","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9080-9836","authenticated-orcid":false,"given":"\u00c1lvaro S.","family":"Hervella","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4407-9091","authenticated-orcid":false,"given":"Jos\u00e9","family":"Rouco","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"Novo","sequence":"additional","affiliation":[]},{"given":"Marcos","family":"Ortega","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2023.11.038_b1","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neunet.2022.03.005","article-title":"SelfVIO: Self-supervised deep monocular visual\u2013Inertial odometry and depth estimation","volume":"150","author":"Almalioglu","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.11.038_b2","doi-asserted-by":"crossref","unstructured":"Bragman, F. J., Tanno, R., Ourselin, S., Alexander, D. C., & Cardoso, J. (2019). Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels. In Proceedings of the IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00147"},{"key":"10.1016\/j.neunet.2023.11.038_b3","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2023.11.038_b4","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.-Y., & Rabinovich, A. (2018). GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks. In Proceedings of the 35th international conference on machine learning."},{"key":"10.1016\/j.neunet.2023.11.038_b5","series-title":"Advances in neural information processing systems (NeurIPS)","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2023.11.038_b6","series-title":"2009 IEEE conference on computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"61","key":"10.1016\/j.neunet.2023.11.038_b7","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2023.11.038_b8","doi-asserted-by":"crossref","unstructured":"Eigen, D., & Fergus, R. (2015). Predicting Depth, Surface Normals and Semantic Labels With a Common Multi-Scale Convolutional Architecture. In Proceedings of the IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.304"},{"key":"10.1016\/j.neunet.2023.11.038_b9","doi-asserted-by":"crossref","first-page":"141627","DOI":"10.1109\/ACCESS.2019.2943604","article-title":"A comparison of loss weighting strategies for multi task learning in deep neural networks","volume":"7","author":"Gong","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2023.11.038_b10","series-title":"Deep learning","author":"Goodfellow","year":"2016"},{"key":"10.1016\/j.neunet.2023.11.038_b11","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.","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"10.1016\/j.neunet.2023.11.038_b12","series-title":"Proceedings of the IEEE international conference on computer vision","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"10.1016\/j.neunet.2023.11.038_b13","series-title":"Proceedings of the IEEE international conference on computer vision","article-title":"Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification","author":"He","year":"2015"},{"key":"10.1016\/j.neunet.2023.11.038_b14","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2023.11.038_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.115598","article-title":"Self-supervised multimodal reconstruction pre-training for retinal computer-aided diagnosis","volume":"185","author":"Hervella","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2023.11.038_b16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2022.02.020","article-title":"TSFD-Net: Tissue specific feature distillation network for nuclei segmentation and classification","volume":"151","author":"Ilyas","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.11.038_b17","unstructured":"Kendall, A., Gal, Y., & Cipolla, R. (2018). Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. CVPR."},{"key":"10.1016\/j.neunet.2023.11.038_b18","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations. (ICLR)."},{"key":"10.1016\/j.neunet.2023.11.038_b19","doi-asserted-by":"crossref","unstructured":"Kosti, R., Alvarez, J. M., Recasens, A., & Lapedriza, A. (2017). Emotion recognition in context. In The IEEE conference on computer vision and pattern recognition. (CVPR).","DOI":"10.1109\/CVPR.2017.212"},{"issue":"11","key":"10.1016\/j.neunet.2023.11.038_b20","first-page":"2755","article-title":"Context based emotion recognition using EMOTIC dataset","volume":"42","author":"Kosti","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.11.038_b21","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., & Davison, A. J. (2019). End-To-End Multi-Task Learning With Attention. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00197"},{"key":"10.1016\/j.neunet.2023.11.038_b22","unstructured":"Loshchilov, I., & Hutter, F. (2019). Decoupled Weight Decay Regularization. In 7th international conference on learning representations."},{"key":"10.1016\/j.neunet.2023.11.038_b23","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3059968","article-title":"Image segmentation using deep learning: A survey","author":"Minaee","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.11.038_b24","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","article-title":"Cross-stitch networks for multi-task learning","author":"Misra","year":"2016"},{"key":"10.1016\/j.neunet.2023.11.038_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104542","article-title":"Emotion recognition: A smoothed Dirichlet multinomial solution","volume":"107","author":"Najar","year":"2022","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2023.11.038_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104205","article-title":"An effective combination of loss gradients for multi-task learning applied on instance segmentation and depth estimation","volume":"100","author":"Nakamura","year":"2021","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2023.11.038_b27","series-title":"Advances in neural information processing systems (NeurIPS), Vol. 31","article-title":"Multi-task learning as multi-objective optimization","author":"Sener","year":"2018"},{"key":"10.1016\/j.neunet.2023.11.038_b28","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor Segmentation and Support Inference from RGBD Images. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"10.1016\/j.neunet.2023.11.038_b29","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 Proceedings of the 37th international conference on machine learning."},{"key":"10.1016\/j.neunet.2023.11.038_b30","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., & Wang, J. (2019). Deep High-Resolution Representation Learning for Human Pose Estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"10.1016\/j.neunet.2023.11.038_b31","series-title":"Lecture 6.5\u2014RmsProp: Divide the gradient by a running average of its recent magnitude","author":"Tieleman","year":"2012"},{"key":"10.1016\/j.neunet.2023.11.038_b32","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3054719","article-title":"Multi-task learning for dense prediction tasks: A survey","author":"Vandenhende","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2023.11.038_b33","doi-asserted-by":"crossref","unstructured":"Vandenhende, S., Georgoulis, S., & Van Gool, L. (2020). MTI-Net: Multi-scale Task Interaction Networks for Multi-task Learning. In Proceedings of the European conference on computer vision.","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"10.1016\/j.neunet.2023.11.038_b34","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 Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00077"},{"key":"10.1016\/j.neunet.2023.11.038_b35","series-title":"Advances in neural information processing systems (NeurIPS)","article-title":"Gradient surgery for multi-task learning","author":"Yu","year":"2020"},{"issue":"11","key":"10.1016\/j.neunet.2023.11.038_b36","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: A review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2023.11.038_b37","series-title":"Advances in neural information processing systems, vol. 27","article-title":"Learning deep features for scene recognition using places database","author":"Zhou","year":"2014"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023006615?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023006615?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:38:52Z","timestamp":1760236732000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608023006615"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":37,"alternative-id":["S0893608023006615"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2023.11.038","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2024,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-Adaptive Optimization for multi-task learning with deep neural networks","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2023.11.038","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}]}}