{"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/panoptic-segmentation-with-a-joint-semantic","title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","arxiv_id":"1809.02110","date":"2018-09-06","proceeding":"CoRR 2019 2","authors":["Daan de Geus","Panagiotis Meletis","Gijs Dubbelman"],"abstract":"We present a single network method for panoptic segmentation. This method\ncombines the predictions from a jointly trained semantic and instance\nsegmentation network using heuristics. Joint training is the first step towards\nan end-to-end panoptic segmentation network and is faster and more memory\nefficient than training and predicting with two networks, as done in previous\nwork. The architecture consists of a ResNet-50 feature extractor shared by the\nsemantic segmentation and instance segmentation branch. For instance\nsegmentation, a Mask R-CNN type of architecture is used, while the semantic\nsegmentation branch is augmented with a Pyramid Pooling Module. Results for\nthis method are submitted to the COCO and Mapillary Joint Recognition Challenge\n2018. Our approach achieves a PQ score of 17.6 on the Mapillary Vistas\nvalidation set and 27.2 on the COCO test-dev set.","url_abs":"http://arxiv.org/abs/1809.02110v2","url_pdf":"http://arxiv.org/pdf/1809.02110v2.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":[],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pyramid-pooling-module","method_name":"Pyramid Pooling Module"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"JSIS-Net","rank_in_archive_order":38,"of":38,"metrics":{"PQ":"27.2","PQst":"23.4","PQth":"29.6"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-mapillary-val","task":"Panoptic Segmentation","dataset":"Mapillary val","model":"JSIS-Net (ResNet-50)","rank_in_archive_order":11,"of":13,"metrics":{"PQ":"17.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.02110","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}