{"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","title":"Panoptic Segmentation","arxiv_id":"1801.00868","date":"2018-01-03","proceeding":"CVPR 2019 6","authors":["Alexander Kirillov","Kaiming He","Ross Girshick","Carsten Rother","Piotr Dollár"],"abstract":"We propose and study a task we name panoptic segmentation (PS). Panoptic\nsegmentation unifies the typically distinct tasks of semantic segmentation\n(assign a class label to each pixel) and instance segmentation (detect and\nsegment each object instance). The proposed task requires generating a coherent\nscene segmentation that is rich and complete, an important step toward\nreal-world vision systems. While early work in computer vision addressed\nrelated image/scene parsing tasks, these are not currently popular, possibly\ndue to lack of appropriate metrics or associated recognition challenges. To\naddress this, we propose a novel panoptic quality (PQ) metric that captures\nperformance for all classes (stuff and things) in an interpretable and unified\nmanner. Using the proposed metric, we perform a rigorous study of both human\nand machine performance for PS on three existing datasets, revealing\ninteresting insights about the task. The aim of our work is to revive the\ninterest of the community in a more unified view of image segmentation.","url_abs":"http://arxiv.org/abs/1801.00868v3","url_pdf":"http://arxiv.org/pdf/1801.00868v3.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":"panoptic-segmentation","repo_url":"https://github.com/cocodataset/panopticapi","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/ChristophReich1996/TYC-Dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/DdeGeus/single-network-panoptic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/banus/umf_unet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/christophreich1996/yeast-in-microstructures-dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/dhassault/panoptic_segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/jlazarow/learning_instance_occlusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/kdethoor/panoptictorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"panoptic-segmentation","repo_url":"https://github.com/looooongchen/sortedap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"scene-parsing","task_name":"Scene Parsing"},{"task_slug":"scene-segmentation","task_name":"Scene 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":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"MRCNN + PSPNet (ResNet-101)","rank_in_archive_order":24,"of":37,"metrics":{"AP":"36.4","PQ":"61.2","PQst":"66.4","PQth":"54"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.00868","atlas_url":"https://app.syntology.ai/?focus=1801.00868","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}