{"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/path-aggregation-network-for-instance","title":"Path Aggregation Network for Instance Segmentation","arxiv_id":"1803.01534","date":"2018-03-05","proceeding":"CVPR 2018 6","authors":["Shu Liu","Lu Qi","Haifang Qin","Jianping Shi","Jiaya Jia"],"abstract":"The way that information propagates in neural networks is of great\nimportance. In this paper, we propose Path Aggregation Network (PANet) aiming\nat boosting information flow in proposal-based instance segmentation framework.\nSpecifically, we enhance the entire feature hierarchy with accurate\nlocalization signals in lower layers by bottom-up path augmentation, which\nshortens the information path between lower layers and topmost feature. We\npresent adaptive feature pooling, which links feature grid and all feature\nlevels to make useful information in each feature level propagate directly to\nfollowing proposal subnetworks. A complementary branch capturing different\nviews for each proposal is created to further improve mask prediction. These\nimprovements are simple to implement, with subtle extra computational overhead.\nOur PANet reaches the 1st place in the COCO 2017 Challenge Instance\nSegmentation task and the 2nd place in Object Detection task without\nlarge-batch training. It is also state-of-the-art on MVD and Cityscapes. Code\nis available at https://github.com/ShuLiu1993/PANet","url_abs":"http://arxiv.org/abs/1803.01534v4","url_pdf":"http://arxiv.org/pdf/1803.01534v4.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":"path-aggregation-network-for-instance","repo_url":"https://github.com/ShuLiu1993/PANet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/CVUsers/Smart-Retail-By-Efficientdet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/YuefeiZ/PANet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/texasinstruments/edgeai-yolov5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/texasinstruments/edgeai-yolox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/ultralytics/yolov5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/wslerry/yolov5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/mindspore-ai/models/tree/master/official/cv/yolov5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"path-aggregation-network-for-instance","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adaptive-feature-pooling","method_name":"Adaptive Feature Pooling"},{"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":"bottom-up-path-augmentation","method_name":"Bottom-up Path Augmentation"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pafpn","method_name":"PAFPN"},{"method_slug":"panet","method_name":"PANet"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnext","method_name":"ResNeXt"},{"method_slug":"resnext-block","method_name":"ResNeXt Block"},{"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":"sgd-with-momentum","method_name":"SGD with Momentum"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"adaptive-feature-pooling","name":"Adaptive Feature Pooling","full_name":"Adaptive Feature Pooling"},{"slug":"pafpn","name":"PAFPN","full_name":"PAFPN"},{"slug":"panet","name":"PANet","full_name":"PANet"}],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"PANet (ResNet-50)","rank_in_archive_order":83,"of":93,"metrics":{"mask AP":"37.8"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"PANet","rank_in_archive_order":56,"of":112,"metrics":{"mask AP":"42.0"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-isaid","task":"Instance Segmentation","dataset":"iSAID","model":"PANet","rank_in_archive_order":5,"of":5,"metrics":{"Average Precision":"34.17"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"PANet (ResNeXt-101, multi-scale)","rank_in_archive_order":118,"of":225,"metrics":{"AP50":"67.2","AP75":"51.8 ","APL":"60.0 ","APM":"51.7","APS":"30.1","box mAP":"47.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-isaid","task":"Object Detection","dataset":"iSAID","model":"PANet","rank_in_archive_order":3,"of":5,"metrics":{"Average Precision":"41.66"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.01534","atlas_url":"https://app.syntology.ai/?focus=1803.01534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.01534"}},"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/ShuLiu1993/PANet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YuefeiZ/PANet","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleDetection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/texasinstruments/edgeai-yolox","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/official/cv/yolov5","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/texasinstruments/edgeai-yolov5","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ultralytics/yolov5","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wslerry/yolov5","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CVUsers/Smart-Retail-By-Efficientdet","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"ae91aee49740c295","entry":"compute_backbone_shapes","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ae91aee49740c295"}},{"code_sha256_prefix":"06e62194f17cd06a","entry":"parse_rec","repo":"ShuLiu1993/PANet","repo_kind":"official","path":"lib/datasets/voc_eval.py","file_url":"https://github.com/ShuLiu1993/PANet/blob/HEAD/lib/datasets/voc_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06e62194f17cd06a"}},{"code_sha256_prefix":"611c47c44c424dba","entry":"voc_ap","repo":"ShuLiu1993/PANet","repo_kind":"official","path":"lib/datasets/voc_eval.py","file_url":"https://github.com/ShuLiu1993/PANet/blob/HEAD/lib/datasets/voc_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"611c47c44c424dba"}},{"code_sha256_prefix":"7177fe851c20e20e","entry":"voc_eval","repo":"ShuLiu1993/PANet","repo_kind":"official","path":"lib/datasets/voc_eval.py","file_url":"https://github.com/ShuLiu1993/PANet/blob/HEAD/lib/datasets/voc_eval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7177fe851c20e20e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}