Pith. sign in

REVIEW 1 cited by

Towards PAC Multi-Object Detection and Tracking

Not yet reviewed by Pith; the record is open.

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 2204.07482 v1 pith:OXPU4OQR submitted 2022-04-15 cs.CV cs.LG

classification cs.CVcs.LG
keywords predictiondetectionguaranteeshighprobabilitytrackingtruealgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation. However, it remains challenging to provide guarantees on the performance of state-of-the-art techniques based on deep learning. We consider a strategy known as conformal prediction, which predicts sets of labels instead of a single label; in the classification and regression settings, these algorithms can guarantee that the true label lies within the prediction set with high probability. Building on these ideas, we propose multi-object detection and tracking algorithms that come with probably approximately correct (PAC) guarantees. They do so by constructing both a prediction set around each object detection as well as around the set of edge transitions; given an object, the detection prediction set contains its true bounding box with high probability, and the edge prediction set contains its true transition across frames with high probability. We empirically demonstrate that our method can detect and track objects with PAC guarantees on the COCO and MOT-17 datasets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Conformal Prediction Sets for Instance Segmentation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A conformal method outputs a set of candidate instance masks per pixel query, guaranteeing that with probability ≥1−α at least one mask has IoU above a threshold.

Pith tools