Papers › Cascade R-CNN: High Quality Object Detection and Instance Segmentation

Cascade R-CNN: High Quality Object Detection and Instance Segmentation

24 Jun 2019arXiv:1906.09756archive 2025-07-28

Zhaowei Cai, Nuno Vasconcelos

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 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 https://github.com/zhaoweicai/cascade-rcnn (Caffe) and https://github.com/zhaoweicai/Detectron-Cascade-RCNN (Detectron).

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

zhaoweicai/Detectron-Cascade-RCNN officialmentioned in papertfApache-2.0Syntology: not harvested report
zhaoweicai/cascade-rcnn officialmentioned in papertfSyntology: not harvested report
open-mmlab/mmdetection mentioned in paperpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Burf/tfdetection tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified), Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationObject DetectionSemantic SegmentationVocal Bursts Intensity Predictionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation BDD100K val Cascade Mask R-CNN AP 19.8 #4 of 4 Archive leaderboard report
Object Detection COCO test-dev Cascade R-CNN AP50 62.1 #169 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade R-CNN AP75 46.3 #169 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade R-CNN APL 55.2 #169 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade R-CNN APM 45.5 #169 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade R-CNN APS 23.7 #169 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade R-CNN Hardware Burden 15G #169 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade R-CNN box mAP 42.8 #169 of 225 Archive leaderboard report
Object Detection COCO-O Cascade R-CNN (ResNet-50) Average mAP 18.2 #34 of 45 Archive leaderboard report
Object Detection COCO-O Cascade R-CNN (ResNet-50) Effective Robustness 0.02 #34 of 45 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Cascade R-CNNConvolutionMask R-CNNRPNRoIAlignSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections