{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/auxiliary-tasks-in-multi-task-learning","title":"Auxiliary Tasks in Multi-task Learning","arxiv_id":"1805.06334","date":"2018-05-16","proceeding":null,"authors":["Lukas Liebel","Marco Körner"],"abstract":"Multi-task convolutional neural networks (CNNs) have shown impressive results\nfor certain combinations of tasks, such as single-image depth estimation (SIDE)\nand semantic segmentation. This is achieved by pushing the network towards\nlearning a robust representation that generalizes well to different atomic\ntasks. We extend this concept by adding auxiliary tasks, which are of minor\nrelevance for the application, to the set of learned tasks. As a kind of\nadditional regularization, they are expected to boost the performance of the\nultimately desired main tasks. To study the proposed approach, we picked\nvision-based road scene understanding (RSU) as an exemplary application. Since\nmulti-task learning requires specialized datasets, particularly when using\nextensive sets of tasks, we provide a multi-modal dataset for multi-task RSU,\ncalled synMT. More than 2.5 $\\cdot$ 10^5 synthetic images, annotated with 21\ndifferent labels, were acquired from the video game Grand Theft Auto V (GTA V).\nOur proposed deep multi-task CNN architecture was trained on various\ncombination of tasks using synMT. The experiments confirmed that auxiliary\ntasks can indeed boost network performance, both in terms of final results and\ntraining time.","url_abs":"http://arxiv.org/abs/1805.06334v2","url_pdf":"http://arxiv.org/pdf/1805.06334v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"auxiliary-tasks-in-multi-task-learning","repo_url":"https://github.com/Mikoto10032/AutomaticWeightedLoss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"auxiliary-tasks-in-multi-task-learning","repo_url":"https://github.com/MindCode-4/code-11/tree/main/auxiliary-tasks-in-multi-task-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"auxiliary-tasks-in-multi-task-learning","repo_url":"https://github.com/MindCode-4/code-6/tree/main/auxiliary-tasks-in-multi-task-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"road-scene-understanding","task_name":"road scene understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.06334","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}