{"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/many-task-learning-with-task-routing","title":"Many Task Learning with Task Routing","arxiv_id":"1903.12117","date":"2019-03-28","proceeding":"ICCV 2019 10","authors":["Gjorgji Strezoski","Nanne van Noord","Marcel Worring"],"abstract":"Typical multi-task learning (MTL) methods rely on architectural adjustments\nand a large trainable parameter set to jointly optimize over several tasks.\nHowever, when the number of tasks increases so do the complexity of the\narchitectural adjustments and resource requirements. In this paper, we\nintroduce a method which applies a conditional feature-wise transformation over\nthe convolutional activations that enables a model to successfully perform a\nlarge number of tasks. To distinguish from regular MTL, we introduce Many Task\nLearning (MaTL) as a special case of MTL where more than 20 tasks are performed\nby a single model. Our method dubbed Task Routing (TR) is encapsulated in a\nlayer we call the Task Routing Layer (TRL), which applied in an MaTL scenario\nsuccessfully fits hundreds of classification tasks in one model. We evaluate\nour method on 5 datasets against strong baselines and state-of-the-art\napproaches.","url_abs":"http://arxiv.org/abs/1903.12117v1","url_pdf":"http://arxiv.org/pdf/1903.12117v1.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":"many-task-learning-with-task-routing","repo_url":"https://github.com/gstrezoski/TaskRouting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.12117","atlas_url":"https://app.syntology.ai/?focus=1903.12117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.12117"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/gstrezoski/TaskRouting","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"4c8bd6d6b66acbd9","entry":"make_layers","repo":"gstrezoski/TaskRouting","repo_kind":"listed","path":"routed_vgg.py","file_url":"https://github.com/gstrezoski/TaskRouting/blob/HEAD/routed_vgg.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":"4c8bd6d6b66acbd9"}},{"code_sha256_prefix":"40b0cc821f1fe2d5","entry":"vgg11","repo":"gstrezoski/TaskRouting","repo_kind":"listed","path":"routed_vgg.py","file_url":"https://github.com/gstrezoski/TaskRouting/blob/HEAD/routed_vgg.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":"40b0cc821f1fe2d5"}},{"code_sha256_prefix":"1cce7b73b2c6e63c","entry":"vgg11_bn","repo":"gstrezoski/TaskRouting","repo_kind":"listed","path":"routed_vgg.py","file_url":"https://github.com/gstrezoski/TaskRouting/blob/HEAD/routed_vgg.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":"1cce7b73b2c6e63c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}