Pith. sign in

REVIEW 2 cited by

A Parallel Implementation of Computing Mean Average Precision

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 2206.09504 v1 pith:JXTCL5OG submitted 2022-06-19 cs.CV cs.AI

A Parallel Implementation of Computing Mean Average Precision

classification cs.CV cs.AI
keywords implementationaverageboundingboxesclassimplementationsinferencemean
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Mean Average Precision (mAP) has been widely used for evaluating the quality of object detectors, but an efficient implementation is still absent. Current implementations can only count true positives (TP's) and false positives (FP's) for one class at a time by looping through every detection of that class sequentially. Not only are these approaches inefficient, but they are also inconvenient for reporting validation mAP during training. We propose a parallelized alternative that can process mini-batches of detected bounding boxes (DTBB's) and ground truth bounding boxes (GTBB's) as inference goes such that mAP can be instantly calculated after inference is finished. Loops and control statements in sequential implementations are replaced with extensive uses of broadcasting, masking, and indexing. All operators involved are supported by popular machine learning frameworks such as PyTorch and TensorFlow. As a result, our implementation is much faster and can easily fit into typical training routines. A PyTorch version of our implementation is available at https://github.com/bwangca/fast-map.

discussion (0)

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

Forward citations

Cited by 2 Pith papers

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

  1. Automating the Wildfire Detection and Scheduling Pipeline with Maneuverable Earth Observation Satellites

    eess.SY 2026-02 unverdicted novelty 5.0

    An integrated pipeline uses CNN-based detection with sensor fusion, Bayesian statistics for flyover updates, and reconfigurable satellite scheduling to enhance wildfire monitoring in simulations based on real locations.

  2. Automating the Wildfire Detection and Scheduling Pipeline with Maneuverable Earth Observation Satellites

    eess.SY 2026-02 conditional novelty 5.0

    A simulated pipeline combining CNN wildfire detection, Bayesian confidence updates, and reconfigurable satellite scheduling automates wildfire monitoring, but it is not validated on real satellite images.