{"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/groupwise-query-specialization-and-quality","title":"Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection","arxiv_id":"2403.17709","date":"2024-03-26","proceeding":"CVPR 2024 1","authors":["Jongha Kim","Jihwan Park","Jinyoung Park","Jinyoung Kim","Sehyung Kim","Hyunwoo J. Kim"],"abstract":"Visual Relationship Detection (VRD) has seen significant advancements with Transformer-based architectures recently. However, we identify two key limitations in a conventional label assignment for training Transformer-based VRD models, which is a process of mapping a ground-truth (GT) to a prediction. Under the conventional assignment, an unspecialized query is trained since a query is expected to detect every relation, which makes it difficult for a query to specialize in specific relations. Furthermore, a query is also insufficiently trained since a GT is assigned only to a single prediction, therefore near-correct or even correct predictions are suppressed by being assigned no relation as a GT. To address these issues, we propose Groupwise Query Specialization and Quality-Aware Multi-Assignment (SpeaQ). Groupwise Query Specialization trains a specialized query by dividing queries and relations into disjoint groups and directing a query in a specific query group solely toward relations in the corresponding relation group. Quality-Aware Multi-Assignment further facilitates the training by assigning a GT to multiple predictions that are significantly close to a GT in terms of a subject, an object, and the relation in between. Experimental results and analyses show that SpeaQ effectively trains specialized queries, which better utilize the capacity of a model, resulting in consistent performance gains with zero additional inference cost across multiple VRD models and benchmarks. Code is available at https://github.com/mlvlab/SpeaQ.","url_abs":"https://arxiv.org/abs/2403.17709v1","url_pdf":"https://arxiv.org/pdf/2403.17709v1.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":"groupwise-query-specialization-and-quality","repo_url":"https://github.com/mlvlab/speaq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Relation"},{"task_slug":"relationship-detection","task_name":"Relationship Detection"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"visual-relationship-detection","task_name":"Visual Relationship Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-graph-generation-on-visual-genome","task":"Scene Graph Generation","dataset":"Visual Genome","model":"SpeaQ (without reweighting)","rank_in_archive_order":1,"of":19,"metrics":{"R@100":"36.0","Recall@100":"36.0","Recall@50":"32.9","mR@100":"14.1","mR@50":"11.8","mean Recall @100":"14.1"},"uses_additional_data":false},{"leaderboard":"/sota/scene-graph-generation-on-visual-genome","task":"Scene Graph Generation","dataset":"Visual Genome","model":"SpeaQ (with reweighting)","rank_in_archive_order":2,"of":19,"metrics":{"R@100":"35.5","Recall@100":"35.5","Recall@50":"32.1","mR@100":"17.6","mR@50":"15.1","mean Recall @100":"17.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.17709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17709"}},"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/mlvlab/speaq","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mlvlab/SpeaQ","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"0f17ae0853df90a4","entry":"gen_sineembed_for_position","repo":"mlvlab/SpeaQ","repo_kind":"official","path":"modeling/transformer/detr.py","file_url":"https://github.com/mlvlab/SpeaQ/blob/HEAD/modeling/transformer/detr.py","link_basis":"first_harvest_node","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":"0f17ae0853df90a4"}},{"code_sha256_prefix":"7d4002289969a288","entry":"argsort_desc","repo":"mlvlab/SpeaQ","repo_kind":"official","path":"evaluation/utils.py","file_url":"https://github.com/mlvlab/SpeaQ/blob/HEAD/evaluation/utils.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":"7d4002289969a288"}},{"code_sha256_prefix":"6727d2d8f1d79998","entry":"intersect_2d","repo":"mlvlab/SpeaQ","repo_kind":"official","path":"evaluation/utils.py","file_url":"https://github.com/mlvlab/SpeaQ/blob/HEAD/evaluation/utils.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":"6727d2d8f1d79998"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}