{"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/multi-task-dense-prediction-via-mixture-of","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","arxiv_id":"2403.17749","date":"2024-03-26","proceeding":"CVPR 2024 1","authors":["YuQi Yang","Peng-Tao Jiang","Qibin Hou","Hao Zhang","Jinwei Chen","Bo Li"],"abstract":"Previous multi-task dense prediction methods based on the Mixture of Experts (MoE) have received great performance but they neglect the importance of explicitly modeling the global relations among all tasks. In this paper, we present a novel decoder-focused method for multi-task dense prediction, called Mixture-of-Low-Rank-Experts (MLoRE). To model the global task relationships, MLoRE adds a generic convolution path to the original MoE structure, where each task feature can go through this path for explicit parameter sharing. Furthermore, to control the parameters and computational cost brought by the increase in the number of experts, we take inspiration from LoRA and propose to leverage the low-rank format of a vanilla convolution in the expert network. Since the low-rank experts have fewer parameters and can be dynamically parameterized into the generic convolution, the parameters and computational cost do not change much with the increase of experts. Benefiting from this design, we increase the number of experts and its reception field to enlarge the representation capacity, facilitating multiple dense tasks learning in a unified network. Extensive experiments on the PASCAL-Context and NYUD-v2 benchmarks show that our MLoRE achieves superior performance compared to previous state-of-the-art methods on all metrics. Our code is available at https://github.com/YuqiYang213/MLoRE.","url_abs":"https://arxiv.org/abs/2403.17749v2","url_pdf":"https://arxiv.org/pdf/2403.17749v2.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":"multi-task-dense-prediction-via-mixture-of","repo_url":"https://github.com/yuqiyang213/mlore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.17749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17749"}},"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/yuqiyang213/mlore","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/YuqiYang213/MLoRE","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_fixture":2,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":11,"samples":[{"code_sha256_prefix":"9ac08340b51f89c7","entry":"Attention","repo":"YuqiYang213/MLoRE","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/YuqiYang213/MLoRE/blob/HEAD/models/transformers/MLoRE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ac08340b51f89c7"}},{"code_sha256_prefix":"39e1e82bab3c6883","entry":"Block","repo":"YuqiYang213/MLoRE","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/YuqiYang213/MLoRE/blob/HEAD/models/transformers/MLoRE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"39e1e82bab3c6883"}},{"code_sha256_prefix":"90ccfb0198123d92","entry":"LoraBlock","repo":"YuqiYang213/MLoRE","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/YuqiYang213/MLoRE/blob/HEAD/models/transformers/MLoRE.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":"90ccfb0198123d92"}},{"code_sha256_prefix":"fb2d8245d587bf16","entry":"SpatialAtt","repo":"YuqiYang213/MLoRE","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/YuqiYang213/MLoRE/blob/HEAD/models/transformers/MLoRE.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":"fb2d8245d587bf16"}},{"code_sha256_prefix":"eda4c531e76e3fa8","entry":"normalize_tensor","repo":"yuqiyang213/mlore","repo_kind":"official","path":"evaluation/eval_normals.py","file_url":"https://github.com/yuqiyang213/mlore/blob/HEAD/evaluation/eval_normals.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eda4c531e76e3fa8"}},{"code_sha256_prefix":"191b2735955d18f4","entry":"resize_pos_embed","repo":"yuqiyang213/mlore","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/yuqiyang213/mlore/blob/HEAD/models/transformers/MLoRE.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"191b2735955d18f4"}},{"code_sha256_prefix":"84cbc8dde894bd57","entry":"sep_prompt","repo":"yuqiyang213/mlore","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/yuqiyang213/mlore/blob/HEAD/models/transformers/MLoRE.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"84cbc8dde894bd57"}},{"code_sha256_prefix":"fbc3b0ecf5603a6a","entry":"transI_fusebn","repo":"yuqiyang213/mlore","repo_kind":"official","path":"models/transformers/MLoRE_repara.py","file_url":"https://github.com/yuqiyang213/mlore/blob/HEAD/models/transformers/MLoRE_repara.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbc3b0ecf5603a6a"}},{"code_sha256_prefix":"e80a12982287fe24","entry":"MLoRE","repo":"YuqiYang213/MLoRE","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/YuqiYang213/MLoRE/blob/HEAD/models/transformers/MLoRE.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":"e80a12982287fe24"}},{"code_sha256_prefix":"41fa052b9167fb6e","entry":"MOEBlock","repo":"YuqiYang213/MLoRE","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/YuqiYang213/MLoRE/blob/HEAD/models/transformers/MLoRE.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":"41fa052b9167fb6e"}},{"code_sha256_prefix":"6d8a1f8a0697180f","entry":"checkpoint_filter_fn","repo":"yuqiyang213/mlore","repo_kind":"official","path":"models/transformers/MLoRE.py","file_url":"https://github.com/yuqiyang213/mlore/blob/HEAD/models/transformers/MLoRE.py","link_basis":"harvester_set","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":"6d8a1f8a0697180f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}