Pith. sign in

REVIEW 3 cited by

Probabilistic two-stage detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.07461 v1 pith:RWN6EI4L submitted 2021-03-12 cs.CV

Probabilistic two-stage detection

Xingyi Zhou , Vladlen Koltun , Philipp Kr\"ahenb\"uhl This is my paper
classification cs.CV
keywords detectortwo-stageprobabilisticdetectionachievescocodetectorsinfer
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection

    cs.CV 2026-04 unverdicted novelty 7.0

    Hierarchical confidence calibration and LoCLIP adaptation improve pseudo-label quality for open-vocabulary object detection, achieving new state-of-the-art results on COCO and LVIS benchmarks.

  2. TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation

    cs.CV 2026-07 conditional novelty 6.0

    Hybrid T2I generation with teacher-student pseudo-labeling plus VRAIN context-aware I2I rare-class editing improves LVIS instance segmentation AP, especially on rare categories.

  3. A Two Stage Pipeline for Left Atrial Wall Constrained Scar Segmentation and Localization from LGE-MR Images

    eess.IV 2026-04 unverdicted novelty 4.0

    A two-stage nnUNet framework with patient-specific signed distance maps and wall-masked loss achieves 61.1% Dice and 1.711 mm ASSD for left atrial scar segmentation on the LAScarQS 2022 dataset.