# SOGNet: Scene Overlap Graph Network for Panoptic Segmentation Source: [SOGNet: Scene Overlap Graph Network for Panoptic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-12-25T07:43:43.208Z Authors: Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin Published: 2019-11-18T10:26:35.000Z ## Abstract The panoptic segmentation task requires a unified result from semantic and instance segmentation outputs that may contain overlaps. However, current studies widely ignore modeling overlaps. In this study, we aim to model overlap relations among instances and resolve them for panoptic segmentation. Inspired by scene graph representation, we formulate the overlapping problem as a simplified case, named scene overlap graph. We leverage each object's category, geometry and appearance features to perform relational embedding, and output a relation matrix that encodes overlap relations. In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances. The mask logits after removing overlaps are fed into per-pixel instance \\verb\|id\| classification, which leverages the panoptic supervision to assist in the modeling of overlap relations. Besides, we generate an approximate ground truth of overlap relations as the weak supervision, to quantify the accuracy of overlap relations predicted by our method. Experiments on COCO and Cityscapes demonstrate that our method is able to accurately predict overlap relations, and outperform the state-of-the-art performance for panoptic segmentation. Our method also won the Innovation Award in COCO 2019 challenge. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Panoptic Segmentation on MS-COCO 2018 (test-dev)](): Panoptic Segmentation; MS-COCO 2018 (test-dev); PQ (Panoptic Quality): 47.8. - [Panoptic Segmentation on COCO 2017 (test-dev)](): Panoptic Segmentation; COCO 2017 (test-dev); PQ: 47.8. - [Panoptic Segmentation on COCO (test-dev)](): Panoptic Segmentation; COCO (test-dev); PQ: 47.8. - [Panoptic Segmentation on COCO (val)](): Panoptic Segmentation; COCO (val); PQ: 43.7. - [Panoptic Segmentation on Cityscapes (val)](): Panoptic Segmentation; Cityscapes (val); PQ: 60. ## Original sources and implementation [Original paper]() [PDF]()