{"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/upsnet-a-unified-panoptic-segmentation","title":"UPSNet: A Unified Panoptic Segmentation Network","arxiv_id":"1901.03784","date":"2019-01-12","proceeding":"CVPR 2019 6","authors":["Yuwen Xiong","Renjie Liao","Hengshuang Zhao","Rui Hu","Min Bai","Ersin Yumer","Raquel Urtasun"],"abstract":"In this paper, we propose a unified panoptic segmentation network (UPSNet)\nfor tackling the newly proposed panoptic segmentation task. On top of a single\nbackbone residual network, we first design a deformable convolution based\nsemantic segmentation head and a Mask R-CNN style instance segmentation head\nwhich solve these two subtasks simultaneously. More importantly, we introduce a\nparameter-free panoptic head which solves the panoptic segmentation via\npixel-wise classification. It first leverages the logits from the previous two\nheads and then innovatively expands the representation for enabling prediction\nof an extra unknown class which helps better resolve the conflicts between\nsemantic and instance segmentation. Additionally, it handles the challenge\ncaused by the varying number of instances and permits back propagation to the\nbottom modules in an end-to-end manner. Extensive experimental results on\nCityscapes, COCO and our internal dataset demonstrate that our UPSNet achieves\nstate-of-the-art performance with much faster inference. Code has been made\navailable at: https://github.com/uber-research/UPSNet","url_abs":"http://arxiv.org/abs/1901.03784v2","url_pdf":"http://arxiv.org/pdf/1901.03784v2.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":"upsnet-a-unified-panoptic-segmentation","repo_url":"https://github.com/uber-research/UPSNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":"deformable-convolution","method_name":"Deformable 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":"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":"UPSNet (ResNet-101-FPN)","rank_in_archive_order":22,"of":38,"metrics":{"PQ":"46.6","PQst":"36.7","PQth":"53.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"UPSNet (ResNet-101, multiscale)","rank_in_archive_order":22,"of":37,"metrics":{"AP":"39.0","PQ":"61.8","PQst":"64.8","PQth":"57.6","mIoU":"79.2"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"UPSNet (ResNet-101)","rank_in_archive_order":26,"of":37,"metrics":{"AP":"37.8","PQ":"60.5","PQst":"63.0","PQth":"57.0","mIoU":"77.8"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"UPSNet (ResNet-50)","rank_in_archive_order":28,"of":37,"metrics":{"AP":"33.3","PQ":"59.3","PQst":"62.7","PQth":"54.6","mIoU":"75.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-indian-driving-1","task":"Panoptic Segmentation","dataset":"Indian Driving Dataset","model":"UPSNet","rank_in_archive_order":3,"of":4,"metrics":{"PQ":"47.1"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-kitti-panoptic-1","task":"Panoptic Segmentation","dataset":"KITTI Panoptic Segmentation","model":"UPSNet","rank_in_archive_order":3,"of":4,"metrics":{"PQ":"39.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.03784","atlas_url":"https://app.syntology.ai/?focus=1901.03784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.03784"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uber-research/UPSNet","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"06fecfcfaf04ff31","entry":"get_step_index","repo":"uber-research/UPSNet","repo_kind":"official","path":"upsnet/upsnet_end2end_train.py","file_url":"https://github.com/uber-research/UPSNet/blob/HEAD/upsnet/upsnet_end2end_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"06fecfcfaf04ff31"}},{"code_sha256_prefix":"d6f5d048e1535eeb","entry":"lr_factor","repo":"uber-research/UPSNet","repo_kind":"official","path":"upsnet/upsnet_end2end_train.py","file_url":"https://github.com/uber-research/UPSNet/blob/HEAD/upsnet/upsnet_end2end_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d6f5d048e1535eeb"}},{"code_sha256_prefix":"93a18ae852753bae","entry":"lr_poly","repo":"uber-research/UPSNet","repo_kind":"official","path":"upsnet/upsnet_end2end_train.py","file_url":"https://github.com/uber-research/UPSNet/blob/HEAD/upsnet/upsnet_end2end_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"93a18ae852753bae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}