{"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/efficient-computation-sharing-for-multi-task","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","arxiv_id":"2303.09663","date":"2023-03-16","proceeding":"ICCV 2023 1","authors":["Sara Shoouri","Mingyu Yang","Zichen Fan","Hun-Seok Kim"],"abstract":"Solving multiple visual tasks using individual models can be resource-intensive, while multi-task learning can conserve resources by sharing knowledge across different tasks. Despite the benefits of multi-task learning, such techniques can struggle with balancing the loss for each task, leading to potential performance degradation. We present a novel computation- and parameter-sharing framework that balances efficiency and accuracy to perform multiple visual tasks utilizing individually-trained single-task transformers. Our method is motivated by transfer learning schemes to reduce computational and parameter storage costs while maintaining the desired performance. Our approach involves splitting the tasks into a base task and the other sub-tasks, and sharing a significant portion of activations and parameters/weights between the base and sub-tasks to decrease inter-task redundancies and enhance knowledge sharing. The evaluation conducted on NYUD-v2 and PASCAL-context datasets shows that our method is superior to the state-of-the-art transformer-based multi-task learning techniques with higher accuracy and reduced computational resources. Moreover, our method is extended to video stream inputs, further reducing computational costs by efficiently sharing information across the temporal domain as well as the task domain. Our codes and models will be publicly available.","url_abs":"https://arxiv.org/abs/2303.09663v2","url_pdf":"https://arxiv.org/pdf/2303.09663v2.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":"efficient-computation-sharing-for-multi-task","repo_url":"https://github.com/sarashoouri/efficientmtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.09663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09663"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/sarashoouri/EfficientMTL","reach":null}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"d969a5ba04920f2e","entry":"Attention","repo":"sarashoouri/EfficientMTL","repo_kind":"official","path":"Codes/multimae/multimae.py","file_url":"https://github.com/sarashoouri/EfficientMTL/blob/HEAD/Codes/multimae/multimae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d969a5ba04920f2e"}},{"code_sha256_prefix":"3cb7e68ce1e3f5f2","entry":"Block","repo":"sarashoouri/EfficientMTL","repo_kind":"official","path":"Codes/multimae/multimae.py","file_url":"https://github.com/sarashoouri/EfficientMTL/blob/HEAD/Codes/multimae/multimae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3cb7e68ce1e3f5f2"}},{"code_sha256_prefix":"e6e9f6bf7f63ce5e","entry":"DropPath","repo":"sarashoouri/EfficientMTL","repo_kind":"official","path":"Codes/multimae/multimae.py","file_url":"https://github.com/sarashoouri/EfficientMTL/blob/HEAD/Codes/multimae/multimae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e6e9f6bf7f63ce5e"}},{"code_sha256_prefix":"ab3aedef666eb507","entry":"MultiMAE","repo":"sarashoouri/EfficientMTL","repo_kind":"official","path":"Codes/multimae/multimae.py","file_url":"https://github.com/sarashoouri/EfficientMTL/blob/HEAD/Codes/multimae/multimae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab3aedef666eb507"}},{"code_sha256_prefix":"f35e6dabc38aa3d0","entry":"MultiViT","repo":"sarashoouri/EfficientMTL","repo_kind":"official","path":"Codes/multimae/multimae.py","file_url":"https://github.com/sarashoouri/EfficientMTL/blob/HEAD/Codes/multimae/multimae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f35e6dabc38aa3d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}