{"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/weakly-and-semi-supervised-panoptic","title":"Weakly- and Semi-Supervised Panoptic Segmentation","arxiv_id":"1808.03575","date":"2018-08-10","proceeding":"ECCV 2018 9","authors":["Qizhu Li","Anurag Arnab","Philip H. S. Torr"],"abstract":"We present a weakly supervised model that jointly performs both semantic- and\ninstance-segmentation -- a particularly relevant problem given the substantial\ncost of obtaining pixel-perfect annotation for these tasks. In contrast to many\npopular instance segmentation approaches based on object detectors, our method\ndoes not predict any overlapping instances. Moreover, we are able to segment\nboth \"thing\" and \"stuff\" classes, and thus explain all the pixels in the image.\n\"Thing\" classes are weakly-supervised with bounding boxes, and \"stuff\" with\nimage-level tags. We obtain state-of-the-art results on Pascal VOC, for both\nfull and weak supervision (which achieves about 95% of fully-supervised\nperformance). Furthermore, we present the first weakly-supervised results on\nCityscapes for both semantic- and instance-segmentation. Finally, we use our\nweakly supervised framework to analyse the relationship between annotation\nquality and predictive performance, which is of interest to dataset creators.","url_abs":"http://arxiv.org/abs/1808.03575v3","url_pdf":"http://arxiv.org/pdf/1808.03575v3.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":"weakly-and-semi-supervised-panoptic","repo_url":"https://github.com/qizhuli/Weakly-Supervised-Panoptic-Segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"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"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-instance-segmentation","task_name":"Weakly-supervised instance segmentation"},{"task_slug":"weakly-supervised-panoptic-segmentation","task_name":"Weakly-supervised panoptic 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":"Dynamically Instantiated Network (ResNet-101)","rank_in_archive_order":34,"of":37,"metrics":{"AP":"28.6","PQ":"53.8","PQst":"62.1","PQth":"42.5","mIoU":"79.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.03575","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}