{"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/reppoints-point-set-representation-for-object","title":"RepPoints: Point Set Representation for Object Detection","arxiv_id":"1904.11490","date":"2019-04-25","proceeding":"ICCV 2019 10","authors":["Ze Yang","Shaohui Liu","Han Hu","Li-Wei Wang","Stephen Lin"],"abstract":"Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse localization of objects and leads to a correspondingly coarse extraction of object features. In this paper, we present \\textbf{RepPoints} (representative points), a new finer representation of objects as a set of sample points useful for both localization and recognition. Given ground truth localization and recognition targets for training, RepPoints learn to automatically arrange themselves in a manner that bounds the spatial extent of an object and indicates semantically significant local areas. They furthermore do not require the use of anchors to sample a space of bounding boxes. We show that an anchor-free object detector based on RepPoints can be as effective as the state-of-the-art anchor-based detection methods, with 46.5 AP and 67.4 $AP_{50}$ on the COCO test-dev detection benchmark, using ResNet-101 model. Code is available at https://github.com/microsoft/RepPoints.","url_abs":"https://arxiv.org/abs/1904.11490v2","url_pdf":"https://arxiv.org/pdf/1904.11490v2.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":"reppoints-point-set-representation-for-object","repo_url":"https://github.com/microsoft/RepPoints","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reppoints-point-set-representation-for-object","repo_url":"https://github.com/Scalsol/RepPointsV2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reppoints-point-set-representation-for-object","repo_url":"https://github.com/kcmeehan/SmartDetect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reppoints-point-set-representation-for-object","repo_url":"https://github.com/muditchaudhary/RepPoints-x-Libra-R-CNN-x-Transformer-self-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reppoints-point-set-representation-for-object","repo_url":"https://github.com/nuannuanhcc/ps_reppoint","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reppoints-point-set-representation-for-object","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":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rpdet","method_name":"RPDet"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"reppoints","method_name":"RepPoints"},{"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":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[{"slug":"rpdet","name":"RPDet","full_name":"RPDet"},{"slug":"reppoints","name":"RepPoints","full_name":"RepPoints"}],"results":[{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"RPDet (ResNeXt-101-DCN, multi-scale)","rank_in_archive_order":101,"of":220,"metrics":{"box AP":"46.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"RPDet (ResNet-101-DCN, multi-scale)","rank_in_archive_order":105,"of":220,"metrics":{"box AP":"46.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"RPDet (ResNet-101-DCN, multi-scale train)","rank_in_archive_order":123,"of":220,"metrics":{"box AP":"44.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"RPDet (ResNeXt-101-DCN)","rank_in_archive_order":130,"of":220,"metrics":{"box AP":"44.5"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"RPDet (ResNet-50, multi-scale train)","rank_in_archive_order":174,"of":220,"metrics":{"box AP":"40.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"RPDet (ResNet-101)","rank_in_archive_order":182,"of":220,"metrics":{"box AP":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"RPDet (ResNet-50)","rank_in_archive_order":194,"of":220,"metrics":{"box AP":"38.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RPDet (ResNet-101-DCN, multi-scale)","rank_in_archive_order":125,"of":225,"metrics":{"AP50":"67.4","AP75":"50.9","APL":"57.1","APM":"49.7","APS":"30.3","box mAP":"46.5"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RPDet (ResNet-101-DCN)","rank_in_archive_order":166,"of":225,"metrics":{"AP50":"65.0","AP75":"46.3","APL":"54.7","APM":"46.2","APS":"24.9","box mAP":"42.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"RPDet (ResNet-101)","rank_in_archive_order":184,"of":225,"metrics":{"AP50":"62.9","AP75":"44.3","APL":"51.7","APM":"44.1","APS":"23.6","box mAP":"41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.11490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11490"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/kcmeehan/SmartDetect","reach":{"status":"ok"}},{"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/Scalsol/RepPointsV2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nuannuanhcc/ps_reppoint","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/RepPoints","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/muditchaudhary/RepPoints-x-Libra-R-CNN-x-Transformer-self-attention","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"listed":{"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":3,"samples":[{"code_sha256_prefix":"e76a491553cf9fcf","entry":"process_checkpoint","repo":"Scalsol/RepPointsV2","repo_kind":"listed","path":".dev_scripts/gather_models.py","file_url":"https://github.com/Scalsol/RepPointsV2/blob/HEAD/.dev_scripts/gather_models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e76a491553cf9fcf"}},{"code_sha256_prefix":"e86ae414e2afc197","entry":"get_final_epoch","repo":"Scalsol/RepPointsV2","repo_kind":"listed","path":".dev_scripts/gather_models.py","file_url":"https://github.com/Scalsol/RepPointsV2/blob/HEAD/.dev_scripts/gather_models.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":false,"mcp_get_code":{"code_sha256":"e86ae414e2afc197"}},{"code_sha256_prefix":"fee6fb3d147348e3","entry":"get_final_results","repo":"Scalsol/RepPointsV2","repo_kind":"listed","path":".dev_scripts/gather_models.py","file_url":"https://github.com/Scalsol/RepPointsV2/blob/HEAD/.dev_scripts/gather_models.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":false,"mcp_get_code":{"code_sha256":"fee6fb3d147348e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}