{"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/mti-net-multi-scale-task-interaction-networks","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","arxiv_id":"2001.06902","date":"2020-01-19","proceeding":"ECCV 2020 8","authors":["Simon Vandenhende","Stamatios Georgoulis","Luc van Gool"],"abstract":"In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a certain scale are not guaranteed to retain this behaviour at other scales, and vice versa. We propose a novel architecture, namely MTI-Net, that builds upon this finding in three ways. First, it explicitly models task interactions at every scale via a multi-scale multi-modal distillation unit. Second, it propagates distilled task information from lower to higher scales via a feature propagation module. Third, it aggregates the refined task features from all scales via a feature aggregation unit to produce the final per-task predictions. Extensive experiments on two multi-task dense labeling datasets show that, unlike prior work, our multi-task model delivers on the full potential of multi-task learning, that is, smaller memory footprint, reduced number of calculations, and better performance w.r.t. single-task learning. The code is made publicly available: https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch.","url_abs":"https://arxiv.org/abs/2001.06902v5","url_pdf":"https://arxiv.org/pdf/2001.06902v5.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":"mti-net-multi-scale-task-interaction-networks","repo_url":"https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1-bit-adam","method_name":"1-bit Adam"},{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"MTI-Net (HRNet-48)","rank_in_archive_order":73,"of":121,"metrics":{"Mean IoU":"49.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-urbanlf","task":"Semantic Segmentation","dataset":"UrbanLF","model":"MTINet (HRNetV2-W48)","rank_in_archive_order":7,"of":14,"metrics":{"mIoU (Real)":"n.a.","mIoU (Syn)":"79.10"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2001.06902","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}