{"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/dsgg-dense-relation-transformer-for-an-end-to","title":"DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation","arxiv_id":"2403.14886","date":"2024-03-21","proceeding":"CVPR 2024 1","authors":["Zeeshan Hayder","Xuming He"],"abstract":"Scene graph generation aims to capture detailed spatial and semantic relationships between objects in an image, which is challenging due to incomplete labelling, long-tailed relationship categories, and relational semantic overlap. Existing Transformer-based methods either employ distinct queries for objects and predicates or utilize holistic queries for relation triplets and hence often suffer from limited capacity in learning low-frequency relationships. In this paper, we present a new Transformer-based method, called DSGG, that views scene graph detection as a direct graph prediction problem based on a unique set of graph-aware queries. In particular, each graph-aware query encodes a compact representation of both the node and all of its relations in the graph, acquired through the utilization of a relaxed sub-graph matching during the training process. Moreover, to address the problem of relational semantic overlap, we utilize a strategy for relation distillation, aiming to efficiently learn multiple instances of semantic relationships. Extensive experiments on the VG and the PSG datasets show that our model achieves state-of-the-art results, showing a significant improvement of 3.5\\% and 6.7\\% in mR@50 and mR@100 for the scene-graph generation task and achieves an even more substantial improvement of 8.5\\% and 10.3\\% in mR@50 and mR@100 for the panoptic scene graph generation task. Code is available at \\url{https://github.com/zeeshanhayder/DSGG}.","url_abs":"https://arxiv.org/abs/2403.14886v1","url_pdf":"https://arxiv.org/pdf/2403.14886v1.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":"dsgg-dense-relation-transformer-for-an-end-to","repo_url":"https://github.com/zeeshanhayder/dsgg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"panoptic-scene-graph-generation","task_name":"Panoptic Scene Graph Generation"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"scene-graph-detection","task_name":"Scene Graph Detection"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.14886","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}