[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84074-en":3,"doc-seo-84074-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84074,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability","Scene graph generation (SGG) methods are commonly divided into detector-based and query-based approaches, yet their prediction discrepancies are not thoroughly analyzed. A controlled experimental setup is designed from the perspective of detector-conditioned reachability, using an external object detector to classify triplets into Det-T and UDet-T. Complementary clues are identified, motivating Dual-SGG, which unifies both reasoning mechanisms via a dual-query design. Experiments on Visual Genome, Open Images v6, and GQA-200 validate effectiveness.","arXiv :2607 .06 176v 1 [ cs .CV] 7 Jul 2026  \nRevisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability  \nRunfeng Qu 1 ,5, Pia K Bideau3, Ole Hall 1 ,5, Julie Ouerfelli-Ethier2 ,5,  \nKlaus Obermayer 1 ,4 ,5, and Olaf Hellwich 1 ,5  \n1 Technische Universität Berlin, Germany  \n2 Humboldt Universität zu Berlin, Germany  \n3 Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, France  \n4 Bernstein Center for Computational Neuroscience, Germany  \n5 Science of Intelligence Research Cluster of Excellence, Germany  \n[runfeng.qu@campus.tu-berlin.de](runfeng.qu@campus.tu-berlin.de)  \nAbstract. Scene graph generation (SGG) approaches can be broadly classified into detector-based and query-based methods according to their underlying reasoning mechanisms. However, the discrepancy in their predictive behaviors, induced by these distinct mechanisms, has not been systematically analyzed. In this work, we design a controlled experimental setup to examine prediction discrepancies from the perspective of detector-conditioned reachability. The results suggest clear complementary clues. Motivated by this observation, we introduce a Dual-SGG method that consolidates both reasoning mechanisms via a dual-query design, thereby leveraging the complementary predictive behaviors of both detector-based and query-based methods. Extensive experiments on the Visual Genome, Open Images v6, and GQA-200 datasets demonstrate the effectiveness of the proposed method. Code is available at:  \nDual-SGG.  \nKeywords: Scene Graph Generation · Visual Relationship Detection · Scene Analysis and Understanding  \n1 Introduction  \nScene graphs represent images as graphs, with nodes as entities and edges as pairwise relations. Each relationship is typically expressed as a (subject, predicate, object) triplet. Because of their high-level image understanding, scene graphs have been widely used in image captioning [33, 43], visual question answering [36], and image generation [13, 24] .  \nExisting scene graph generation (SGG) approaches can be broadly categorized into detector-based and query-based methods according to their underlying reasoning mechanisms. Detector-based models employ an internal object detector to localize entities and subsequently perform reasoning over pairs of detected entities to predict triplets. Conceptually, these models exhibit difficulties in predicting triplets whose subject or object instances are semantically or  \n2 R. Qu et al.  \nFig. 1: SGG Models. (a) Detector-based model. (b) Query-based model. (c) Querybased model that additionally incorporates entity information derived from an object detector. (d) The proposed Dual-SGG method, which integrates detector-based and query-based reasoning mechanisms within a unified triplet decoder.  \nspatially uncovered by detections from the employed object detector. Here, we term this problem the detector constraint. To eliminate this detector constraint, query-based models introduce learnable triplet queries, inspired by the detection transformer (DETR) [1] paradigm, thereby enabling end-to-end triplet prediction without the need to enumerate entity pairs explicitly. In current studies, SGG models are predominantly evaluated using aggregate metrics such as Recall and mean-Recall, which quantify overall triplet prediction performance. However, these aggregate metrics do not elucidate the distinct predictive behaviors induced by the differing reasoning mechanisms. In particular, it remains unclear whether query-based models offer improvements on triplets that are challenging for detector-based models to detect due to the detector constraint.  \nTo bridge this gap, we design a controlled experimental setup on the Visual Genome (VG) [17] dataset to compare prediction behaviors from the perspective of detector-conditioned reachability. To this end, we pre-train an external object detector that serves as a discriminator, determining whether a triplet is reachable for a detector-base","cbCaiuCpYpYT1YUx","https://ap.wps.com/l/cbCaiuCpYpYT1YUx","pdf",2646326,4,1,19,"English","en",105,"# Abstract\n# Introduction\n## Scene graph generation background\n## Detector constraint and detector-conditioned reachability\n## Experimental setup and datasets","[{\"question\":\"What is the core idea behind Dual-SGG?\",\"answer\":\"Dual-SGG uses a dual-query design to consolidate detector-based and query-based reasoning mechanisms, leveraging their complementary predictive behaviors.\"}]",1784192505,48,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"revisiting-scene-graph-generation-from-the-perspective-of-detector-conditioned-reachability","",{"@graph":36,"@context":77},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/revisiting-scene-graph-generation-from-the-perspective-of-detector-conditioned-reachability/84074/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What is the core idea behind Dual-SGG?","Question",{"text":75,"@type":76},"Dual-SGG uses a dual-query design to consolidate detector-based and query-based reasoning mechanisms, leveraging their complementary predictive behaviors.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},"General","general"]