{"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/cross-task-attention-mechanism-for-dense","title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","arxiv_id":"2206.08927","date":"2022-06-17","proceeding":null,"authors":["Ivan Lopes","Tuan-Hung Vu","Raoul de Charette"],"abstract":"Multi-task learning has recently emerged as a promising solution for a comprehensive understanding of complex scenes. In addition to being memory-efficient, multi-task models, when appropriately designed, can facilitate the exchange of complementary signals across tasks. In this work, we jointly address 2D semantic segmentation and three geometry-related tasks: dense depth estimation, surface normal estimation, and edge estimation, demonstrating their benefits on both indoor and outdoor datasets. We propose a novel multi-task learning architecture that leverages pairwise cross-task exchange through correlation-guided attention and self-attention to enhance the overall representation learning for all tasks. We conduct extensive experiments across three multi-task setups, showing the advantages of our approach compared to competitive baselines in both synthetic and real-world benchmarks. Additionally, we extend our method to the novel multi-task unsupervised domain adaptation setting. Our code is available at https://github.com/cv-rits/DenseMTL","url_abs":"https://arxiv.org/abs/2206.08927v2","url_pdf":"https://arxiv.org/pdf/2206.08927v2.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":"cross-task-attention-mechanism-for-dense","repo_url":"https://github.com/astra-vision/densemtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cross-task-attention-mechanism-for-dense","repo_url":"https://github.com/cv-rits/densemtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2d-semantic-segmentation","task_name":"2D Semantic Segmentation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"DenseMTL","rank_in_archive_order":109,"of":121,"metrics":{"Mean IoU":"40.84%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.08927","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}