{"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-r-cnn-delving-into-high-quality","title":"Cascade R-CNN: Delving into High Quality Object Detection","arxiv_id":"1712.00726","date":"2017-12-03","proceeding":"CVPR 2018 6","authors":["Zhaowei Cai","Nuno Vasconcelos"],"abstract":"In object detection, an intersection over union (IoU) threshold is required\nto define positives and negatives. An object detector, trained with low IoU\nthreshold, e.g. 0.5, usually produces noisy detections. However, detection\nperformance tends to degrade with increasing the IoU thresholds. Two main\nfactors are responsible for this: 1) overfitting during training, due to\nexponentially vanishing positive samples, and 2) inference-time mismatch\nbetween the IoUs for which the detector is optimal and those of the input\nhypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is\nproposed to address these problems. It consists of a sequence of detectors\ntrained with increasing IoU thresholds, to be sequentially more selective\nagainst close false positives. The detectors are trained stage by stage,\nleveraging the observation that the output of a detector is a good distribution\nfor training the next higher quality detector. The resampling of progressively\nimproved hypotheses guarantees that all detectors have a positive set of\nexamples of equivalent size, reducing the overfitting problem. The same cascade\nprocedure is applied at inference, enabling a closer match between the\nhypotheses and the detector quality of each stage. A simple implementation of\nthe Cascade R-CNN is shown to surpass all single-model object detectors on the\nchallenging COCO dataset. Experiments also show that the Cascade R-CNN is\nwidely applicable across detector architectures, achieving consistent gains\nindependently of the baseline detector strength. The code will be made\navailable at https://github.com/zhaoweicai/cascade-rcnn.","url_abs":"http://arxiv.org/abs/1712.00726v1","url_pdf":"http://arxiv.org/pdf/1712.00726v1.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-delving-into-high-quality","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-delving-into-high-quality","repo_url":"https://github.com/makefile/frcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"cascade-r-cnn-delving-into-high-quality","repo_url":"https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"cascade-r-cnn-delving-into-high-quality","repo_url":"https://github.com/tkuanlun350/Kaggle_Ship_Detection_2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"cascade-r-cnn-delving-into-high-quality","repo_url":"https://github.com/tsbiosky/Cascade-point-rcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"cascade-r-cnn-delving-into-high-quality","repo_url":"https://github.com/Burf/tfdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"cascade-r-cnn-delving-into-high-quality","repo_url":"https://github.com/PaddlePaddle/PaddleDetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null},{"paper_slug":"cascade-r-cnn-delving-into-high-quality","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":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"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":"cascade-mask-r-cnn","method_name":"Cascade Mask R-CNN"},{"method_slug":"cascade-r-cnn","method_name":"Cascade R-CNN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"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":"group-normalization","method_name":"Group Normalization"},{"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":"position-sensitive-roi-pooling","method_name":"Position-Sensitive RoI Pooling"},{"method_slug":"r-fcn","method_name":"R-FCN"},{"method_slug":"rpn","method_name":"RPN"},{"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":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"cascade-mask-r-cnn","name":"Cascade Mask R-CNN","full_name":"Cascade Mask R-CNN"},{"slug":"cascade-r-cnn","name":"Cascade R-CNN","full_name":"Cascade R-CNN"}],"results":[{"leaderboard":"/sota/2d-object-detection-on-sardet-100k","task":"2D Object Detection","dataset":"SARDet-100K","model":"Cascade R-CNN","rank_in_archive_order":6,"of":13,"metrics":{"box mAP":"51.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-ai-tod","task":"Object Detection","dataset":"AI-TOD","model":"Cascade R-CNN (ResNet-50-FPN)","rank_in_archive_order":6,"of":7,"metrics":{"AP":"13.8","AP50":"30.8","AP75":"10.5","APm":"26.6","APs":"25.5","APt":"10.6","APvt":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Cascade R-CNN (ResNet-101-FPN+, cascade)","rank_in_archive_order":150,"of":220,"metrics":{"AP50":"61.6","AP75":"46.6","APL":"57.4","APM":"46.2","APS":"23.8","box AP":"42.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"Cascade R-CNN (ResNet-50-FPN+)","rank_in_archive_order":180,"of":220,"metrics":{"AP50":" 59.4","AP75":"43.7","APL":"54.1","APM":"43.7","APS":"22.9","box AP":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Cascade R-CNN (ResNet-101-FPN+, cascade)","rank_in_archive_order":168,"of":225,"metrics":{"AP50":"62.1","AP75":"46.3","APL":"55.2","APM":"45.5","APS":"23.7","box mAP":"42.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Cascade R-CNN (ResNet-50-FPN+, cascade)","rank_in_archive_order":189,"of":225,"metrics":{"AP50":"59.9","AP75":"44","APL":"52.1","APM":"42.7","APS":"22.6","Hardware Burden":"12G","box mAP":"40.6"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Cascade R-CNN (ResNet-101-FPN+)","rank_in_archive_order":209,"of":225,"metrics":{"AP50":"61.1","AP75":"41.9","APL":"49.8","APM":"41.8","APS":"21.3","Hardware Burden":"3G","box mAP":"38.8"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Cascade R-CNN (ResNet-50-FPN+)","rank_in_archive_order":222,"of":225,"metrics":{"AP50":"59","AP75":"39.2","APL":"46.4","APM":"38.8","APS":"20.3","Hardware Burden":"3G","box mAP":"36.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.00726","atlas_url":"https://app.syntology.ai/?focus=1712.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00726"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/open-mmlab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleDetection","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tkuanlun350/Kaggle_Ship_Detection_2018","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhaoweicai/cascade-rcnn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tsbiosky/Cascade-point-rcnn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/makefile/frcnn","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Burf/tfdetection","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{},"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":2,"samples":[{"code_sha256_prefix":"bae007593bd3dfd1","entry":"create_logger","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"bae007593bd3dfd1"}},{"code_sha256_prefix":"c349bc6f8ed16220","entry":"create_logger","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c349bc6f8ed16220"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}