{"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/end-to-end-multi-task-learning-with-attention","title":"End-to-End Multi-Task Learning with Attention","arxiv_id":"1803.10704","date":"2018-03-28","proceeding":"CVPR 2019 6","authors":["Shikun Liu","Edward Johns","Andrew J. Davison"],"abstract":"We propose a novel multi-task learning architecture, which allows learning of\ntask-specific feature-level attention. Our design, the Multi-Task Attention\nNetwork (MTAN), consists of a single shared network containing a global feature\npool, together with a soft-attention module for each task. These modules allow\nfor learning of task-specific features from the global features, whilst\nsimultaneously allowing for features to be shared across different tasks. The\narchitecture can be trained end-to-end and can be built upon any feed-forward\nneural network, is simple to implement, and is parameter efficient. We evaluate\nour approach on a variety of datasets, across both image-to-image predictions\nand image classification tasks. We show that our architecture is\nstate-of-the-art in multi-task learning compared to existing methods, and is\nalso less sensitive to various weighting schemes in the multi-task loss\nfunction. Code is available at https://github.com/lorenmt/mtan.","url_abs":"http://arxiv.org/abs/1803.10704v2","url_pdf":"http://arxiv.org/pdf/1803.10704v2.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":"end-to-end-multi-task-learning-with-attention","repo_url":"https://github.com/lorenmt/mtan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"end-to-end-multi-task-learning-with-attention","repo_url":"https://github.com/VICO-UoE/KD4MTL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"end-to-end-multi-task-learning-with-attention","repo_url":"https://github.com/akarimoon/xtask_mt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"end-to-end-multi-task-learning-with-attention","repo_url":"https://github.com/salomonhotegni/mdmtn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.10704","atlas_url":"https://app.syntology.ai/?focus=1803.10704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10704"}},"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/lorenmt/mtan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salomonhotegni/mdmtn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VICO-UoE/KD4MTL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/akarimoon/xtask_mt","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"listed":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"lorenmt/mtan","repo_kind":"official","path":"im2im_pred/model_resnet_mtan/resnet.py","file_url":"https://github.com/lorenmt/mtan/blob/HEAD/im2im_pred/model_resnet_mtan/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"lorenmt/mtan","repo_kind":"official","path":"im2im_pred/model_resnet_mtan/resnet.py","file_url":"https://github.com/lorenmt/mtan/blob/HEAD/im2im_pred/model_resnet_mtan/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"00e569acd6b45ef0","entry":"conv3x3","repo":"lorenmt/mtan","repo_kind":"official","path":"visual_decathlon/model_wrn_mtan.py","file_url":"https://github.com/lorenmt/mtan/blob/HEAD/visual_decathlon/model_wrn_mtan.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00e569acd6b45ef0"}},{"code_sha256_prefix":"9d99831edbfb2a6d","entry":"compute_loss","repo":"akarimoon/xtask_mt","repo_kind":"listed","path":"main_cross_cs.py","file_url":"https://github.com/akarimoon/xtask_mt/blob/HEAD/main_cross_cs.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":"9d99831edbfb2a6d"}},{"code_sha256_prefix":"05f4ecd442041e15","entry":"compute_loss","repo":"akarimoon/xtask_mt","repo_kind":"listed","path":"main_cross_nyu.py","file_url":"https://github.com/akarimoon/xtask_mt/blob/HEAD/main_cross_nyu.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":"05f4ecd442041e15"}},{"code_sha256_prefix":"ae95ce4d85d1083a","entry":"compute_loss_with_gradnorm","repo":"akarimoon/xtask_mt","repo_kind":"listed","path":"main_cross_cs.py","file_url":"https://github.com/akarimoon/xtask_mt/blob/HEAD/main_cross_cs.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":"ae95ce4d85d1083a"}},{"code_sha256_prefix":"9761a56e050ee183","entry":"compute_loss_with_gradnorm","repo":"akarimoon/xtask_mt","repo_kind":"listed","path":"main_cross_nyu.py","file_url":"https://github.com/akarimoon/xtask_mt/blob/HEAD/main_cross_nyu.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":"9761a56e050ee183"}},{"code_sha256_prefix":"8cb280994b68ba9b","entry":"data_transform","repo":"lorenmt/mtan","repo_kind":"official","path":"visual_decathlon/model_wrn_mtan.py","file_url":"https://github.com/lorenmt/mtan/blob/HEAD/visual_decathlon/model_wrn_mtan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cb280994b68ba9b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}