{"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/attentive-single-tasking-of-multiple-tasks","title":"Attentive Single-Tasking of Multiple Tasks","arxiv_id":"1904.08918","date":"2019-04-18","proceeding":"CVPR 2019 6","authors":["Kevis-Kokitsi Maninis","Ilija Radosavovic","Iasonas Kokkinos"],"abstract":"In this work we address task interference in universal networks by\nconsidering that a network is trained on multiple tasks, but performs one task\nat a time, an approach we refer to as \"single-tasking multiple tasks\". The\nnetwork thus modifies its behaviour through task-dependent feature adaptation,\nor task attention. This gives the network the ability to accentuate the\nfeatures that are adapted to a task, while shunning irrelevant ones. We further\nreduce task interference by forcing the task gradients to be statistically\nindistinguishable through adversarial training, ensuring that the common\nbackbone architecture serving all tasks is not dominated by any of the\ntask-specific gradients. Results in three multi-task dense labelling problems\nconsistently show: (i) a large reduction in the number of parameters while\npreserving, or even improving performance and (ii) a smooth trade-off between\ncomputation and multi-task accuracy. We provide our system's code and\npre-trained models at http://vision.ee.ethz.ch/~kmaninis/astmt/.","url_abs":"http://arxiv.org/abs/1904.08918v1","url_pdf":"http://arxiv.org/pdf/1904.08918v1.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":"attentive-single-tasking-of-multiple-tasks","repo_url":"https://github.com/facebookresearch/astmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attentive-single-tasking-of-multiple-tasks","repo_url":"https://github.com/nikola3794/composite-tasking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.08918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08918"}},"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/facebookresearch/astmt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nikola3794/composite-tasking","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"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":1,"samples":[{"code_sha256_prefix":"abc4a58e124ae661","entry":"get_lr_params","repo":"facebookresearch/astmt","repo_kind":"listed","path":"fblib/networks/deeplab_multi_task/deeplab_se_resnet_multitask.py","file_url":"https://github.com/facebookresearch/astmt/blob/HEAD/fblib/networks/deeplab_multi_task/deeplab_se_resnet_multitask.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"abc4a58e124ae661"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}