{"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/cascade-rpn-delving-into-high-quality-region","title":"Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution","arxiv_id":"1909.06720","date":"2019-09-15","proceeding":"NeurIPS 2019 12","authors":["Thang Vu","Hyunjun Jang","Trung X. Pham","Chang D. Yoo"],"abstract":"This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection performance by \\textit{systematically} addressing the limitation of the conventional RPN that \\textit{heuristically defines} the anchors and \\textit{aligns} the features to the anchors. First, instead of using multiple anchors with predefined scales and aspect ratios, Cascade RPN relies on a \\textit{single anchor} per location and performs multi-stage refinement. Each stage is progressively more stringent in defining positive samples by starting out with an anchor-free metric followed by anchor-based metrics in the ensuing stages. Second, to attain alignment between the features and the anchors throughout the stages, \\textit{adaptive convolution} is proposed that takes the anchors in addition to the image features as its input and learns the sampled features guided by the anchors. A simple implementation of a two-stage Cascade RPN achieves AR 13.4 points higher than that of the conventional RPN, surpassing any existing region proposal methods. When adopting to Fast R-CNN and Faster R-CNN, Cascade RPN can improve the detection mAP by 3.1 and 3.5 points, respectively. The code is made publicly available at \\url{https://github.com/thangvubk/Cascade-RPN.git}.","url_abs":"https://arxiv.org/abs/1909.06720v2","url_pdf":"https://arxiv.org/pdf/1909.06720v2.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":"cascade-rpn-delving-into-high-quality-region","repo_url":"https://github.com/thangvubk/Cascade-RPN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cascade-rpn-delving-into-high-quality-region","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-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fast-r-cnn","method_name":"Fast R-CNN"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Faster R-CNN (Cascade RPN)","rank_in_archive_order":190,"of":225,"metrics":{"AP50":"58.9","AP75":"44.5","APL":"52.6","APM":"42.8","APS":"22.0","Hardware Burden":"5G","box mAP":"40.6"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Fast R-CNN (Cascade RPN)","rank_in_archive_order":198,"of":225,"metrics":{"AP50":"59.4","AP75":"43.8","APL":"51.6","APM":"42.4","APS":"22.1","Hardware Burden":"5G","box mAP":"40.1"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1909.06720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}