{"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/grid-r-cnn","title":"Grid R-CNN","arxiv_id":"1811.12030","date":"2018-11-29","proceeding":"CVPR 2019 6","authors":["Xin Lu","Buyu Li","Yuxin Yue","Quanquan Li","Junjie Yan"],"abstract":"This paper proposes a novel object detection framework named Grid R-CNN,\nwhich adopts a grid guided localization mechanism for accurate object\ndetection. Different from the traditional regression based methods, the Grid\nR-CNN captures the spatial information explicitly and enjoys the position\nsensitive property of fully convolutional architecture. Instead of using only\ntwo independent points, we design a multi-point supervision formulation to\nencode more clues in order to reduce the impact of inaccurate prediction of\nspecific points. To take the full advantage of the correlation of points in a\ngrid, we propose a two-stage information fusion strategy to fuse feature maps\nof neighbor grid points. The grid guided localization approach is easy to be\nextended to different state-of-the-art detection frameworks. Grid R-CNN leads\nto high quality object localization, and experiments demonstrate that it\nachieves a 4.1% AP gain at IoU=0.8 and a 10.0% AP gain at IoU=0.9 on COCO\nbenchmark compared to Faster R-CNN with Res50 backbone and FPN architecture.","url_abs":"http://arxiv.org/abs/1811.12030v1","url_pdf":"http://arxiv.org/pdf/1811.12030v1.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":"grid-r-cnn","repo_url":"https://github.com/STVIR/Grid-R-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"grid-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":"2d-object-detection","task_name":"2D Object Detection"},{"task_slug":"novel-object-detection","task_name":"Novel Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"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":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grid-r-cnn","method_name":"Grid R-CNN"},{"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":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"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":"roipool","method_name":"RoIPool"},{"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":"syncbn","method_name":"SyncBN"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"grid-r-cnn","name":"Grid R-CNN","full_name":"Grid R-CNN"}],"results":[{"leaderboard":"/sota/2d-object-detection-on-sardet-100k","task":"2D Object Detection","dataset":"SARDet-100K","model":"Grid RCNN","rank_in_archive_order":10,"of":13,"metrics":{"box mAP":"48.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Grid R-CNN (ResNet-101-FPN)","rank_in_archive_order":165,"of":220,"metrics":{"AP50":"60.3","AP75":"44.4","APL":"54.1","APM":"45.8","APS":"23.4","box AP":"41.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Grid R-CNN (ResNet-50-FPN)","rank_in_archive_order":187,"of":220,"metrics":{"AP50":"58.3","AP75":"42.4","APL":"51.5","APM":"43.8","APS":"22.6","box AP":"39.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Grid R-CNN (ResNeXt-101-FPN)","rank_in_archive_order":160,"of":225,"metrics":{"AP50":"63.0","AP75":"46.6","APL":"55.2","APM":"46.5","APS":"25.1","box mAP":"43.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.12030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12030"}},"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/STVIR/Grid-R-CNN","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"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":0,"samples":[{"code_sha256_prefix":"a7c69b397e5d84e5","entry":"grid_target","repo":"STVIR/Grid-R-CNN","repo_kind":"listed","path":"mmdet/core/mask/grid_target.py","file_url":"https://github.com/STVIR/Grid-R-CNN/blob/HEAD/mmdet/core/mask/grid_target.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":"a7c69b397e5d84e5"}},{"code_sha256_prefix":"592d6a7af571845d","entry":"random_jitter_single","repo":"STVIR/Grid-R-CNN","repo_kind":"listed","path":"mmdet/core/mask/grid_target.py","file_url":"https://github.com/STVIR/Grid-R-CNN/blob/HEAD/mmdet/core/mask/grid_target.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":"592d6a7af571845d"}},{"code_sha256_prefix":"1bd410548921f582","entry":"reduce_vision","repo":"STVIR/Grid-R-CNN","repo_kind":"listed","path":"mmdet/core/mask/grid_target.py","file_url":"https://github.com/STVIR/Grid-R-CNN/blob/HEAD/mmdet/core/mask/grid_target.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":"1bd410548921f582"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}