{"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/mask-scoring-r-cnn","title":"Mask Scoring R-CNN","arxiv_id":"1903.00241","date":"2019-03-01","proceeding":"CVPR 2019 6","authors":["Zhaojin Huang","Lichao Huang","Yongchao Gong","Chang Huang","Xinggang Wang"],"abstract":"Letting a deep network be aware of the quality of its own predictions is an\ninteresting yet important problem. In the task of instance segmentation, the\nconfidence of instance classification is used as mask quality score in most\ninstance segmentation frameworks. However, the mask quality, quantified as the\nIoU between the instance mask and its ground truth, is usually not well\ncorrelated with classification score. In this paper, we study this problem and\npropose Mask Scoring R-CNN which contains a network block to learn the quality\nof the predicted instance masks. The proposed network block takes the instance\nfeature and the corresponding predicted mask together to regress the mask IoU.\nThe mask scoring strategy calibrates the misalignment between mask quality and\nmask score, and improves instance segmentation performance by prioritizing more\naccurate mask predictions during COCO AP evaluation. By extensive evaluations\non the COCO dataset, Mask Scoring R-CNN brings consistent and noticeable gain\nwith different models, and outperforms the state-of-the-art Mask R-CNN. We hope\nour simple and effective approach will provide a new direction for improving\ninstance segmentation. The source code of our method is available at\n\\url{https://github.com/zjhuang22/maskscoring_rcnn}.","url_abs":"http://arxiv.org/abs/1903.00241v1","url_pdf":"http://arxiv.org/pdf/1903.00241v1.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":"mask-scoring-r-cnn","repo_url":"https://github.com/zjhuang22/maskscoring_rcnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mask-scoring-r-cnn","repo_url":"https://github.com/MS-Mind/MS-Code-08/tree/main/MTCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"mask-scoring-r-cnn","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":"classification","task_name":"General Classification"},{"task_slug":"instance-segmentation","task_name":"Instance 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":"fpn","method_name":"FPN"},{"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":"mask-scoring-r-cnn","method_name":"Mask Scoring 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/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Mask Scoring R-CNN (ResNet-101-FPN-DCN)","rank_in_archive_order":78,"of":93,"metrics":{"mask AP":"39.1"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Mask Scoring R-CNN (ResNet-101 FPN)","rank_in_archive_order":82,"of":93,"metrics":{"mask AP":"38.2"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"Mask Scoring R-CNN (ResNet-50 FPN)","rank_in_archive_order":87,"of":93,"metrics":{"mask AP":"36.0"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"MS R-CNN + ResNet-101 DCN + FPN","rank_in_archive_order":79,"of":112,"metrics":{"mask AP":"39.6%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.00241","atlas_url":"https://app.syntology.ai/?focus=1903.00241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00241"}},"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/MS-Mind/MS-Code-08/tree/main/MTCNN","reach":null},{"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/zjhuang22/maskscoring_rcnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"e261fa29066b37e5","entry":"smooth_l1_loss","repo":"zjhuang22/maskscoring_rcnn","repo_kind":"official","path":"maskrcnn_benchmark/layers/smooth_l1_loss.py","file_url":"https://github.com/zjhuang22/maskscoring_rcnn/blob/HEAD/maskrcnn_benchmark/layers/smooth_l1_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e261fa29066b37e5"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"zjhuang22/maskscoring_rcnn","repo_kind":"official","path":"maskrcnn_benchmark/layers/misc.py","file_url":"https://github.com/zjhuang22/maskscoring_rcnn/blob/HEAD/maskrcnn_benchmark/layers/misc.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":"2902bf4410253ff7"}},{"code_sha256_prefix":"5ab322eae8b53480","entry":"l2_loss","repo":"zjhuang22/maskscoring_rcnn","repo_kind":"official","path":"maskrcnn_benchmark/layers/l2_loss.py","file_url":"https://github.com/zjhuang22/maskscoring_rcnn/blob/HEAD/maskrcnn_benchmark/layers/l2_loss.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":"5ab322eae8b53480"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}