{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/cascade-r-cnn-high-quality-object-detection","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","arxiv_id":"1906.09756","date":"2019-06-24","proceeding":null,"authors":["Zhaowei Cai","Nuno Vasconcelos"],"abstract":"In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its \\textit{quality}. While the commonly used threshold of 0.5 leads to noisy (low-quality) detections, detection performance frequently degrades for larger thresholds. This paradox of high-quality detection has two causes: 1) overfitting, due to vanishing positive samples for large thresholds, and 2) inference-time quality mismatch between detector and test hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, composed of a sequence of detectors trained with increasing IoU thresholds, is proposed to address these problems. The detectors are trained sequentially, using the output of a detector as training set for the next. This resampling progressively improves hypotheses quality, guaranteeing a positive training set of equivalent size for all detectors and minimizing overfitting. The same cascade is applied at inference, to eliminate quality mismatches between hypotheses and detectors. An implementation of the Cascade R-CNN without bells or whistles achieves state-of-the-art performance on the COCO dataset, and significantly improves high-quality detection on generic and specific object detection datasets, including VOC, KITTI, CityPerson, and WiderFace. Finally, the Cascade R-CNN is generalized to instance segmentation, with nontrivial improvements over the Mask R-CNN. To facilitate future research, two implementations are made available at \\url{https://github.com/zhaoweicai/cascade-rcnn} (Caffe) and \\url{https://github.com/zhaoweicai/Detectron-Cascade-RCNN} (Detectron).","url_abs":"https://arxiv.org/abs/1906.09756v1","url_pdf":"https://arxiv.org/pdf/1906.09756v1.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-r-cnn-high-quality-object-detection","repo_url":"https://github.com/zhaoweicai/Detectron-Cascade-RCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cascade-r-cnn-high-quality-object-detection","repo_url":"https://github.com/zhaoweicai/cascade-rcnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"cascade-r-cnn-high-quality-object-detection","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cascade-r-cnn-high-quality-object-detection","repo_url":"https://github.com/Burf/tfdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"cascade-r-cnn","method_name":"Cascade R-CNN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-bdd100k-val","task":"Instance Segmentation","dataset":"BDD100K val","model":"Cascade Mask R-CNN","rank_in_archive_order":4,"of":4,"metrics":{"AP":"19.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Cascade R-CNN","rank_in_archive_order":169,"of":225,"metrics":{"AP50":"62.1","AP75":"46.3","APL":"55.2","APM":"45.5","APS":"23.7","Hardware Burden":"15G","box mAP":"42.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"Cascade R-CNN\n(ResNet-50)","rank_in_archive_order":34,"of":45,"metrics":{"Average mAP":"18.2","Effective Robustness":"0.02"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.09756","atlas_url":"https://app.syntology.ai/?focus=1906.09756","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1906.09756"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1906.09756\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1906.09756"},"call":"get_concepts_for_paper(arxiv_id=\"1906.09756\")"}],"by_repo":[{"repo":"zhaoweicai/Detectron-Cascade-RCNN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zhaoweicai/cascade-rcnn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"open-mmlab/mmdetection","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.02361"],"harvested_for_calls":[{"arxiv_id":"2401.02361","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.02361"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.02361\")"}]},{"repo":"Burf/tfdetection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1506.01497","1605.07146","1802.02611","2103.14030"],"harvested_for_calls":[{"arxiv_id":"1506.01497","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1506.01497"},"call":"get_harvested_code_for_paper(arxiv_id=\"1506.01497\")"},{"arxiv_id":"1605.07146","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1605.07146"},"call":"get_harvested_code_for_paper(arxiv_id=\"1605.07146\")"},{"arxiv_id":"1802.02611","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1802.02611"},"call":"get_harvested_code_for_paper(arxiv_id=\"1802.02611\")"},{"arxiv_id":"2103.14030","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.14030"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.14030\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3aa7701a1f30fa06d376da3c01f5363e8949ebff115e950db94e68a5058fb3da","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}