{"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/dq-det-learning-dynamic-query-combinations","title":"Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation","arxiv_id":"2307.12239","date":"2023-07-23","proceeding":null,"authors":["Yiming Cui","Linjie Yang","Haichao Yu"],"abstract":"Transformer-based detection and segmentation methods use a list of learned detection queries to retrieve information from the transformer network and learn to predict the location and category of one specific object from each query. We empirically find that random convex combinations of the learned queries are still good for the corresponding models. We then propose to learn a convex combination with dynamic coefficients based on the high-level semantics of the image. The generated dynamic queries, named modulated queries, better capture the prior of object locations and categories in the different images. Equipped with our modulated queries, a wide range of DETR-based models achieve consistent and superior performance across multiple tasks including object detection, instance segmentation, panoptic segmentation, and video instance segmentation.","url_abs":"https://arxiv.org/abs/2307.12239v2","url_pdf":"https://arxiv.org/pdf/2307.12239v2.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":"dq-det-learning-dynamic-query-combinations","repo_url":"https://github.com/bytedance/dq-det","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.12239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12239"}},"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":"deterministic:regex_extraction","url":"https://github.com/bytedance/DQ-Det","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bytedance/dq-det","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"ac8fe530cdad4d8c","entry":"dice_loss","repo":"bytedance/DQ-Det","repo_kind":"official","path":"Cond-DETR-DQ/models/segmentation.py","file_url":"https://github.com/bytedance/DQ-Det/blob/HEAD/Cond-DETR-DQ/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac8fe530cdad4d8c"}},{"code_sha256_prefix":"5c0711aada67957e","entry":"sigmoid_focal_loss","repo":"bytedance/DQ-Det","repo_kind":"official","path":"Cond-DETR-DQ/models/segmentation.py","file_url":"https://github.com/bytedance/DQ-Det/blob/HEAD/Cond-DETR-DQ/models/segmentation.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c0711aada67957e"}},{"code_sha256_prefix":"86f65ed94e4398da","entry":"build_transformer","repo":"bytedance/DQ-Det","repo_kind":"official","path":"Cond-DETR-DQ/models/transformer.py","file_url":"https://github.com/bytedance/DQ-Det/blob/HEAD/Cond-DETR-DQ/models/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86f65ed94e4398da"}},{"code_sha256_prefix":"d573d92393e20123","entry":"gen_sineembed_for_position","repo":"bytedance/DQ-Det","repo_kind":"official","path":"Cond-DETR-DQ/models/transformer.py","file_url":"https://github.com/bytedance/DQ-Det/blob/HEAD/Cond-DETR-DQ/models/transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d573d92393e20123"}},{"code_sha256_prefix":"f09175b0f39f0ad0","entry":"multi_head_attention_forward","repo":"bytedance/DQ-Det","repo_kind":"official","path":"Cond-DETR-DQ/models/attention.py","file_url":"https://github.com/bytedance/DQ-Det/blob/HEAD/Cond-DETR-DQ/models/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f09175b0f39f0ad0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}