Pith. sign in

REVIEW 7 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

Xingyi Zhou , Vladlen Koltun , Philipp Krähenbühl This is my paper · ORCID
classification cs.CV
keywords detectortwo-stageprobabilisticdetectionachievescocodetectorsinfer
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

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). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. 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 of 10

    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.

  2. Embodied Domain Adaptation for Object Detection

    cs.RO 2025-06 conditional novelty 6.0 of 10

    EDAOD adapts open-vocabulary object detectors to new indoor scenes via temporal instance clustering and contrastive learning, outperforming source-free baselines on a new benchmark.

  3. Corner2Net: Detecting Objects as Cascade Corners

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Corner2Net detects objects as cascade corners, predicting class-agnostic top-left corners first and instance-specific bottom-right corners in each RoI, and claims state-of-the-art among corner-based detectors.

  4. Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection

    cs.CV 2024-12 conditional novelty 5.0 of 10

    Prova replaces coarse class-name embeddings with multi-modal prototypes from descriptions and reference images, improving vast-vocabulary detection on V3Det by up to 6.2 AP.

  5. Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perception

    cs.CV 2025-09 reject novelty 4.0 of 10

    Fusing softmax confidence with embedding-space Gaussian mixture entropy improves open-set rejection in air-to-air UAV detection, reporting about 0.88 AUROC on real flight data.

  6. DEYOLO: Dual-Feature-Enhancement YOLO for Cross-Modality Object Detection

    cs.CV 2024-12 conditional novelty 4.0 of 10

    DEYOLO fuses RGB and infrared features with dual channel and spatial enhancement modules and reports improved object detection accuracy on the M3FD and LLVIP datasets.

  7. Introducing a multiscale feature integration network for inpainting with applications to enhanced CMB map reconstruction

    astro-ph.CO 2025-01

Pith tools