{"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/centermask-real-time-anchor-free-instance-1","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","arxiv_id":"1911.06667","date":"2019-11-15","proceeding":"arXiv 2019 11","authors":["Youngwan Lee","Jongyoul Park"],"abstract":"We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detector (FCOS) in the same vein with Mask R-CNN. Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise. We also present an improved backbone networks, VoVNetV2, with two effective strategies: (1) residual connection for alleviating the optimization problem of larger VoVNet \\cite{lee2019energy} and (2) effective Squeeze-Excitation (eSE) dealing with the channel information loss problem of original SE. With SAG-Mask and VoVNetV2, we deign CenterMask and CenterMask-Lite that are targeted to large and small models, respectively. Using the same ResNet-101-FPN backbone, CenterMask achieves 38.3%, surpassing all previous state-of-the-art methods while at a much faster speed. CenterMask-Lite also outperforms the state-of-the-art by large margins at over 35fps on Titan Xp. We hope that CenterMask and VoVNetV2 can serve as a solid baseline of real-time instance segmentation and backbone network for various vision tasks, respectively. The Code is available at https://github.com/youngwanLEE/CenterMask.","url_abs":"https://arxiv.org/abs/1911.06667v6","url_pdf":"https://arxiv.org/pdf/1911.06667v6.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":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/youngwanLEE/CenterMask","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/hades12580/centermask2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/mahdi-darvish/Cloud_Segmentation_using_Mask_R-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/mahdi-darvish/centermask","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/suvasis/birdnet2cs231n","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/youngwanLEE/centermask2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/youngwanLEE/vovnet-detectron2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"centermask-real-time-anchor-free-instance-1","repo_url":"https://github.com/zhuoyang125/CenterMask2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"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":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"real-time-instance-segmentation","task_name":"Real-time Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-instance-segmentation","task_name":"Semi-Supervised Instance 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":"centermask","method_name":"CenterMask"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"effective-squeeze-and-excitation-block","method_name":"Effective Squeeze-and-Excitation Block"},{"method_slug":"fcos","method_name":"FCOS"},{"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":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"osa-identity-mapping-ese","method_name":"OSA (identity mapping + eSE)"},{"method_slug":"one-shot-aggregation","method_name":"One-Shot Aggregation"},{"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":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-attention-guided-mask","method_name":"Spatial Attention-Guided Mask"},{"method_slug":"vovnet","method_name":"VoVNet"},{"method_slug":"vovnetv2","method_name":"VoVNetV2"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"osa-identity-mapping-ese","name":"OSA (identity mapping + eSE)","full_name":"OSA (identity mapping + eSE)"},{"slug":"spatial-attention-guided-mask","name":"Spatial Attention-Guided Mask","full_name":"Spatial Attention-Guided Mask"},{"slug":"vovnetv2","name":"VoVNetV2","full_name":"VoVNetV2"}],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"CenterMask-VoVNetV2-99 (multi-scale)","rank_in_archive_order":64,"of":93,"metrics":{"mask AP":"42.5"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","task":"Instance Segmentation","dataset":"COCO minival","model":"CenterMask-VoVNetV2-99-3x","rank_in_archive_order":76,"of":93,"metrics":{"mask AP":"40.2"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"CenterMask + VoVNet99","rank_in_archive_order":57,"of":112,"metrics":{"APL":"54.3","APM":"44.4","APS":"24.4","mask AP":"41.8"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"CenterMask + VoVNetV2-99 (single-scale)","rank_in_archive_order":68,"of":112,"metrics":{"AP50":"62.3","AP75":"44.1","APL":"57.0","APM":"42.8","APS":"20.1","mask AP":"40.6"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"CenterMask + X101-32x8d (single-scale)","rank_in_archive_order":77,"of":112,"metrics":{"AP50":"61.2","AP75":"42.9","APS":"19.7","mask AP":"39.6"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"CenterMask + ResNet-101-FPN","rank_in_archive_order":86,"of":112,"metrics":{"mask AP":"38.3"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"CenterMask + VoVNetV2-99 (multi-scale)","rank_in_archive_order":109,"of":112,"metrics":{"AP50":"66.2","AP75":"47.4","APS":"27.2"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"CenterMask + VoVNetV2-57 (single-scale)","rank_in_archive_order":110,"of":112,"metrics":{"AP50":"60.8","APM":"41.7","APS":"19.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"CenterMask+VoVNet99 (multi-scale)","rank_in_archive_order":87,"of":220,"metrics":{"AP50":"67.8","box AP":"48.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"CenterMask+VoVNetV2-99 (single-scale)","rank_in_archive_order":113,"of":220,"metrics":{"APL":"58.8","APS":"29.2","box AP":"45.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Mask R-CNN (VoVNetV2-99, single-scale)","rank_in_archive_order":121,"of":220,"metrics":{"APL":"57.7","APS":"28.5","box AP":"44.9"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"CenterMask+VoVNetV2-57 (single-scale)","rank_in_archive_order":126,"of":220,"metrics":{"APM":"48.3","APS":"27.7","box AP":"44.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"CenterMask+X101-32x8d (single-scale)","rank_in_archive_order":131,"of":220,"metrics":{"APL":"57.1","APS":"26.7","box AP":"44.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"CenterMask+VoVNetV2-99 (single-scale)","rank_in_archive_order":136,"of":225,"metrics":{"AP50":"64.5","APL":"57.6","APM":"48.3","APS":"27.8","box mAP":"45.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"CenterMask+VoVNet2-57 (single-scale)","rank_in_archive_order":142,"of":225,"metrics":{"AP50":"63.1","AP75":"48.6","APL":"55.9","APS":"27.1","box mAP":"44.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"CenterMask + X-101-32x8d (single-scale)","rank_in_archive_order":145,"of":225,"metrics":{"AP50":"63.4","AP75":"48.4","APM":"47.2","box mAP":"44.6"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-instance-segmentation-on-mscoco","task":"Real-time Instance Segmentation","dataset":"MSCOCO","model":"CenterMask-Lite (ResNet-50-FPN)","rank_in_archive_order":16,"of":22,"metrics":{"APL":"48.7","APM":"34.7","APS":"12.9","mask AP":"32.9"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-4","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 1% labeled data","model":"CenterMask2 (ResNet50)","rank_in_archive_order":3,"of":3,"metrics":{"mask AP":"10.07"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-7","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 10% labeled data","model":"CenterMask2 (ResNet50)","rank_in_archive_order":3,"of":3,"metrics":{"mask AP":"22.08"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-5","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 2% labeled data","model":"CenterMask2 (ResNet50)","rank_in_archive_order":3,"of":3,"metrics":{"mask AP":"13.46"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on-coco-6","task":"Semi-Supervised Instance Segmentation","dataset":"COCO 5% labeled data","model":"CenterMask2 (ResNet50)","rank_in_archive_order":3,"of":3,"metrics":{"mask AP":"18.04"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.06667","atlas_url":"https://app.syntology.ai/?focus=1911.06667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06667"}},"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/mahdi-darvish/centermask","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hades12580/centermask2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/youngwanLEE/centermask2","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/suvasis/birdnet2cs231n","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/youngwanLEE/vovnet-detectron2","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhuoyang125/CenterMask2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/youngwanLEE/CenterMask","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mahdi-darvish/Cloud_Segmentation_using_Mask_R-CNN","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"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":2,"samples":[{"code_sha256_prefix":"f017532fc389cbfe","entry":"str2bool","repo":"youngwanLEE/CenterMask","repo_kind":"official","path":"demo/centermask_demo.py","file_url":"https://github.com/youngwanLEE/CenterMask/blob/HEAD/demo/centermask_demo.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f017532fc389cbfe"}},{"code_sha256_prefix":"60b0f812f48bb79a","entry":"Max","repo":"hades12580/centermask2","repo_kind":"listed","path":"centermask/layers/wrappers.py","file_url":"https://github.com/hades12580/centermask2/blob/HEAD/centermask/layers/wrappers.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":false,"mcp_get_code":{"code_sha256":"60b0f812f48bb79a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}