Papers › Probabilistic two-stage detection
Probabilistic two-stage detection
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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