{"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-deeplab-a-simple-strong-and-fast","title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","arxiv_id":"1911.10194","date":"2019-11-22","proceeding":"CVPR 2020 6","authors":["Bowen Cheng","Maxwell D. Collins","Yukun Zhu","Ting Liu","Thomas S. Huang","Hartwig Adam","Liang-Chieh Chen"],"abstract":"In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve comparable performance of two-stage methods while yielding fast inference speed. In particular, Panoptic-DeepLab adopts the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively. The semantic segmentation branch is the same as the typical design of any semantic segmentation model (e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression. As a result, our single Panoptic-DeepLab simultaneously ranks first at all three Cityscapes benchmarks, setting the new state-of-art of 84.2% mIoU, 39.0% AP, and 65.5% PQ on test set. Additionally, equipped with MobileNetV3, Panoptic-DeepLab runs nearly in real-time with a single 1025x2049 image (15.8 frames per second), while achieving a competitive performance on Cityscapes (54.1 PQ% on test set). On Mapillary Vistas test set, our ensemble of six models attains 42.7% PQ, outperforming the challenge winner in 2018 by a healthy margin of 1.5%. Finally, our Panoptic-DeepLab also performs on par with several top-down approaches on the challenging COCO dataset. For the first time, we demonstrate a bottom-up approach could deliver state-of-the-art results on panoptic segmentation.","url_abs":"https://arxiv.org/abs/1911.10194v3","url_pdf":"https://arxiv.org/pdf/1911.10194v3.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-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/bowenc0221/panoptic-deeplab","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/AbhinavAtrishi/semisupervised-multitask-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/KenYu910645/perspective-aware-convolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/mistasse/modulom-panopticdeeplab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/sithu31296/panoptic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/JohnnyHopp/Panoptic-DeepLab-Mobilenetv2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/google-research/deeplab2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"panoptic-deeplab-a-simple-strong-and-fast","repo_url":"https://github.com/tensorflow/models/tree/master/official/projects/panoptic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"hard-swish","method_name":"Hard Swish"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"relu6","method_name":"ReLU6"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-cityscapes","task":"Instance Segmentation","dataset":"Cityscapes test","model":"Panoptic-DeepLab [Mapillary Vistas]","rank_in_archive_order":3,"of":11,"metrics":{},"uses_additional_data":true},{"leaderboard":"/sota/instance-segmentation-on-cityscapes","task":"Instance Segmentation","dataset":"Cityscapes test","model":"Panoptic-DeepLab [Cityscapes-fine]","rank_in_archive_order":4,"of":11,"metrics":{},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"Panoptic-DeepLab (Xception-71)","rank_in_archive_order":31,"of":38,"metrics":{"PQ":"41.4","PQst":"35.9","PQth":"45.1"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-test","task":"Panoptic Segmentation","dataset":"Cityscapes test","model":"Panoptic-Deeplab","rank_in_archive_order":6,"of":10,"metrics":{"PQ":"65.5"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"Panoptic-DeepLab (X71)","rank_in_archive_order":18,"of":37,"metrics":{"AP":"38.5","PQ":"64.1","mIoU":"81.5"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-mapillary-val","task":"Panoptic Segmentation","dataset":"Mapillary val","model":"Panoptic-DeepLab (X71)","rank_in_archive_order":8,"of":13,"metrics":{"PQ":"40.5"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"Panoptic-DeepLab","rank_in_archive_order":11,"of":105,"metrics":{"Mean IoU (class)":"84.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"Panoptic-DeepLab","rank_in_archive_order":43,"of":99,"metrics":{"mIoU":"81.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.10194","atlas_url":"https://app.syntology.ai/?focus=1911.10194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.10194"}},"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/google-research/deeplab2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sithu31296/panoptic-segmentation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/official/projects/panoptic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KenYu910645/perspective-aware-convolution","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JohnnyHopp/Panoptic-DeepLab-Mobilenetv2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mistasse/modulom-panopticdeeplab","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AbhinavAtrishi/semisupervised-multitask-learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bowenc0221/panoptic-deeplab","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":7,"ran":4,"repositories":3}},"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":0,"samples":[{"code_sha256_prefix":"27434020b6a1ebd3","entry":"check_depth_map","repo":"KenYu910645/perspective-aware-convolution","repo_kind":"listed","path":"visualDet3D/data_augmentation/scene_aware_data_generator.py","file_url":"https://github.com/KenYu910645/perspective-aware-convolution/blob/HEAD/visualDet3D/data_augmentation/scene_aware_data_generator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27434020b6a1ebd3"}},{"code_sha256_prefix":"20fbfa2279e1ce4b","entry":"div_up","repo":"KenYu910645/perspective-aware-convolution","repo_kind":"listed","path":"demo/kitti_eval/rotate_iou.py","file_url":"https://github.com/KenYu910645/perspective-aware-convolution/blob/HEAD/demo/kitti_eval/rotate_iou.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20fbfa2279e1ce4b"}},{"code_sha256_prefix":"3415a0d1c950c1c7","entry":"get_image_index_str","repo":"KenYu910645/perspective-aware-convolution","repo_kind":"listed","path":"demo/kitti_eval/kitti_common.py","file_url":"https://github.com/KenYu910645/perspective-aware-convolution/blob/HEAD/demo/kitti_eval/kitti_common.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3415a0d1c950c1c7"}},{"code_sha256_prefix":"02566da69866c48c","entry":"trunc_normal_","repo":"sithu31296/panoptic-segmentation","repo_kind":"listed","path":"popseg/models/backbones/layers.py","file_url":"https://github.com/sithu31296/panoptic-segmentation/blob/HEAD/popseg/models/backbones/layers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02566da69866c48c"}},{"code_sha256_prefix":"5bfc727bc2e8984f","entry":"build_loss_from_cfg","repo":"bowenc0221/panoptic-deeplab","repo_kind":"official","path":"segmentation/model/build.py","file_url":"https://github.com/bowenc0221/panoptic-deeplab/blob/HEAD/segmentation/model/build.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5bfc727bc2e8984f"}},{"code_sha256_prefix":"81ed4dfaf58b96e3","entry":"build_segmentation_model_from_cfg","repo":"bowenc0221/panoptic-deeplab","repo_kind":"official","path":"segmentation/model/build.py","file_url":"https://github.com/bowenc0221/panoptic-deeplab/blob/HEAD/segmentation/model/build.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81ed4dfaf58b96e3"}},{"code_sha256_prefix":"e75291bd524307bd","entry":"build_segmentation_model_from_cfg","repo":"mistasse/modulom-panopticdeeplab","repo_kind":"listed","path":"segmentation/model/build.py","file_url":"https://github.com/mistasse/modulom-panopticdeeplab/blob/HEAD/segmentation/model/build.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e75291bd524307bd"}},{"code_sha256_prefix":"c8b847449b3be5dc","entry":"get_image_path","repo":"KenYu910645/perspective-aware-convolution","repo_kind":"listed","path":"demo/kitti_eval/kitti_common.py","file_url":"https://github.com/KenYu910645/perspective-aware-convolution/blob/HEAD/demo/kitti_eval/kitti_common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c8b847449b3be5dc"}},{"code_sha256_prefix":"f027b5ae160547ce","entry":"get_kitti_info_path","repo":"KenYu910645/perspective-aware-convolution","repo_kind":"listed","path":"demo/kitti_eval/kitti_common.py","file_url":"https://github.com/KenYu910645/perspective-aware-convolution/blob/HEAD/demo/kitti_eval/kitti_common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f027b5ae160547ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}