{"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/taskonomy-disentangling-task-transfer","title":"Taskonomy: Disentangling Task Transfer Learning","arxiv_id":"1804.08328","date":"2018-04-23","proceeding":"CVPR 2018 6","authors":["Amir Zamir","Alexander Sax","William Shen","Leonidas Guibas","Jitendra Malik","Silvio Savarese"],"abstract":"Do visual tasks have a relationship, or are they unrelated? For instance,\ncould having surface normals simplify estimating the depth of an image?\nIntuition answers these questions positively, implying existence of a structure\namong visual tasks. Knowing this structure has notable values; it is the\nconcept underlying transfer learning and provides a principled way for\nidentifying redundancies across tasks, e.g., to seamlessly reuse supervision\namong related tasks or solve many tasks in one system without piling up the\ncomplexity.\n  We proposes a fully computational approach for modeling the structure of\nspace of visual tasks. This is done via finding (first and higher-order)\ntransfer learning dependencies across a dictionary of twenty six 2D, 2.5D, 3D,\nand semantic tasks in a latent space. The product is a computational taxonomic\nmap for task transfer learning. We study the consequences of this structure,\ne.g. nontrivial emerged relationships, and exploit them to reduce the demand\nfor labeled data. For example, we show that the total number of labeled\ndatapoints needed for solving a set of 10 tasks can be reduced by roughly 2/3\n(compared to training independently) while keeping the performance nearly the\nsame. We provide a set of tools for computing and probing this taxonomical\nstructure including a solver that users can employ to devise efficient\nsupervision policies for their use cases.","url_abs":"http://arxiv.org/abs/1804.08328v1","url_pdf":"http://arxiv.org/pdf/1804.08328v1.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":"taskonomy-disentangling-task-transfer","repo_url":"https://github.com/StanfordVL/taskonomy","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[{"slug":"taskonomy","name":"Taskonomy","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.08328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.08328"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/StanfordVL/taskonomy","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"876fa76111aafc8a","entry":"passthrough","repo":"StanfordVL/taskonomy","repo_kind":"official","path":"code/lib/models/transfer_models.py","file_url":"https://github.com/StanfordVL/taskonomy/blob/HEAD/code/lib/models/transfer_models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"876fa76111aafc8a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}