{"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/1st-place-solution-for-psg-competition-with","title":"1st Place Solution for PSG competition with ECCV'22 SenseHuman Workshop","arxiv_id":"2302.02651","date":"2023-02-06","proceeding":null,"authors":["Qixun Wang","Xiaofeng Guo","Haofan Wang"],"abstract":"Panoptic Scene Graph (PSG) generation aims to generate scene graph representations based on panoptic segmentation instead of rigid bounding boxes. Existing PSG methods utilize one-stage paradigm which simultaneously generates scene graphs and predicts semantic segmentation masks or two-stage paradigm that first adopt an off-the-shelf panoptic segmentor, then pairwise relationship prediction between these predicted objects. One-stage approach despite having a simplified training paradigm, its segmentation results are usually under-satisfactory, while two-stage approach lacks global context and leads to low performance on relation prediction. To bridge this gap, in this paper, we propose GRNet, a Global Relation Network in two-stage paradigm, where the pre-extracted local object features and their corresponding masks are fed into a transformer with class embeddings. To handle relation ambiguity and predicate classification bias caused by long-tailed distribution, we formulate relation prediction in the second stage as a multi-class classification task with soft label. We conduct comprehensive experiments on OpenPSG dataset and achieve the state-of-art performance on the leadboard. We also show the effectiveness of our soft label strategy for long-tailed classes in ablation studies. Our code has been released in https://github.com/wangqixun/mfpsg.","url_abs":"https://arxiv.org/abs/2302.02651v1","url_pdf":"https://arxiv.org/pdf/2302.02651v1.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":"1st-place-solution-for-psg-competition-with","repo_url":"https://github.com/wangqixun/mfpsg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"1st-place-solution-for-psg-competition-with","repo_url":"https://github.com/luodian/relateanything","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"predicate-classification","task_name":"Predicate Classification"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-network","task_name":"Relation Network"},{"task_slug":"relation-prediction","task_name":"Relation Prediction"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}