{"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/region-proposal-by-guided-anchoring","title":"Region Proposal by Guided Anchoring","arxiv_id":"1901.03278","date":"2019-01-10","proceeding":"CVPR 2019 6","authors":["Jiaqi Wang","Kai Chen","Shuo Yang","Chen Change Loy","Dahua Lin"],"abstract":"Region anchors are the cornerstone of modern object detection techniques.\nState-of-the-art detectors mostly rely on a dense anchoring scheme, where\nanchors are sampled uniformly over the spatial domain with a predefined set of\nscales and aspect ratios. In this paper, we revisit this foundational stage.\nOur study shows that it can be done much more effectively and efficiently.\nSpecifically, we present an alternative scheme, named Guided Anchoring, which\nleverages semantic features to guide the anchoring. The proposed method jointly\npredicts the locations where the center of objects of interest are likely to\nexist as well as the scales and aspect ratios at different locations. On top of\npredicted anchor shapes, we mitigate the feature inconsistency with a feature\nadaption module. We also study the use of high-quality proposals to improve\ndetection performance. The anchoring scheme can be seamlessly integrated into\nproposal methods and detectors. With Guided Anchoring, we achieve 9.1% higher\nrecall on MS COCO with 90% fewer anchors than the RPN baseline. We also adopt\nGuided Anchoring in Fast R-CNN, Faster R-CNN and RetinaNet, respectively\nimproving the detection mAP by 2.2%, 2.7% and 1.2%. Code will be available at\nhttps://github.com/open-mmlab/mmdetection.","url_abs":"http://arxiv.org/abs/1901.03278v2","url_pdf":"http://arxiv.org/pdf/1901.03278v2.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":"region-proposal-by-guided-anchoring","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"region-proposal-by-guided-anchoring","repo_url":"https://github.com/code-implementation1/Code9/tree/main/RetinaFace_ResNet50","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"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":"fpn","method_name":"FPN"},{"method_slug":"fast-r-cnn","method_name":"Fast R-CNN"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"guided-anchoring","method_name":"Guided Anchoring"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"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":"retinanet","method_name":"RetinaNet"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"guided-anchoring","name":"Guided Anchoring","full_name":"Guided Anchoring"}],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"GA-Faster-RCNN","rank_in_archive_order":200,"of":225,"metrics":{"AP50":"59.2","AP75":"43.5","APL":"50.7","APM":"42.6","APS":"21.8","box mAP":"39.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.03278","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}