Papers › Probabilistic two-stage detection

Probabilistic two-stage detection

12 Mar 2021arXiv:2103.07461archive 2025-07-28

Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl

We develop a probabilistic interpretation of two-stage object detection. We show that this probabilistic interpretation motivates a number of common empirical training practices. It also suggests changes to two-stage detection pipelines. Specifically, the first stage should infer proper object-vs-background likelihoods, which should then inform the overall score of the detector. A standard region proposal network (RPN) cannot infer this likelihood sufficiently well, but many one-stage detectors can. We show how to build a probabilistic two-stage detector from any state-of-the-art one-stage detector. The resulting detectors are faster and more accurate than both their one- and two-stage precursors. Our detector achieves 56.4 mAP on COCO test-dev with single-scale testing, outperforming all published results. Using a lightweight backbone, our detector achieves 49.2 mAP on COCO at 33 fps on a Titan Xp, outperforming the popular YOLOv4 model.

PaperPDFCode

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

Code

xingyizhou/CenterNet2 officialmentioned in papermentioned on GitHubpytorch report
aim-uofa/DiverGen mentioned on GitHubpytorchBSD-2-Clause report
smart-car-lab/Centernet2-mmdetction mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

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

Tasks

Object DetectionRegion ProposalVocal Bursts Valence Predictionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale) AP50 74.0 #42 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale) AP75 61.6 #42 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale) APL 68.6 #42 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale) APM 59.7 #42 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale) APS 38.7 #42 of 225 Archive leaderboard report
Object Detection COCO test-dev CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale) box mAP 56.4 #42 of 225 Archive leaderboard report
Object Detection COCO-O CenterNet2 (R2-101-DCN) Average mAP 29.5 #20 of 45 Archive leaderboard report
Object Detection COCO-O CenterNet2 (R2-101-DCN) Effective Robustness 4.29 #20 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

1x1 ConvolutionAverage PoolingConvolutionFPNMax Pooling

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