TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Object Counting

Object Counting

28 benchmarks158 papers

The goal of Object Counting task is to count the number of object instances in a single image or video sequence. It has many real-world applications such as traffic flow monitoring, crowdedness estimation, and product counting.

<span class="description-source">Source: Learning to Count Objects with Few Exemplar Annotations </span>

Benchmarks

Object Counting on FSC147

MAE(test)RMSE(test)MAE(val)RMSE(val)AP50(test)AP(test)MAE

Object Counting on CARPK

MAERMSE

Object Counting on Pascal VOC 2007 count-test

mRMSEmRMSE-nzm-reIRMSE-nzm-relRMSE

Object Counting on COCO count-test

m-reIRMSEm-reIRMSE-nzmRMSEmRMSE-nz

Object Counting on TallyQA-Complex

AccuracyRMSE

Object Counting on TallyQA-Simple

AccuracyRMSE

Object Counting on HowMany-QA

AccuracyRMSE

Object Counting on PASCAL VOC

mRMSE

Object Counting on Omnicount-191

mRMSE

Object Counting on TRANCOS

MAEMSE

Object Counting on Zero Shot Counting on FSC147

MAE(test)