Object Counting On Pascal Voc 2007 Count Test
Metrics
m-reIRMSE-nz
m-relRMSE
mRMSE
mRMSE-nz
Results
Performance results of various models on this benchmark
Model Name | m-reIRMSE-nz | m-relRMSE | mRMSE | mRMSE-nz | Paper Title | Repository |
|---|---|---|---|---|---|---|
| glance-noft-2L | 0.73 | 0.27 | 0.50 | 1.83 | Counting Everyday Objects in Everyday Scenes | |
| Seq-sub-ft-3x3 | 0.68 | 0.22 | 0.43 | 1.65 | Counting Everyday Objects in Everyday Scenes | |
| ens | 0.65 | 0.20 | 0.42 | 1.68 | Counting Everyday Objects in Everyday Scenes | |
| Fast-RCNN | 0.85 | 0.26 | 0.50 | 1.92 | Counting Everyday Objects in Everyday Scenes | |
| Supervised Density Map | 0.61 | 0.17 | 0.29 | 1.14 | Object Counting and Instance Segmentation with Image-level Supervision | |
| Omnicount | - | - | 0.0023 | 0.009 | OmniCount: Multi-label Object Counting with Semantic-Geometric Priors | - |
| LC-ResFCN | 0.61 | 0.17 | 0.31 | 1.20 | Where are the Blobs: Counting by Localization with Point Supervision | |
| LC-PSPNet | 0.70 | 0.20 | 0.35 | 1.32 | Where are the Blobs: Counting by Localization with Point Supervision |
0 of 8 row(s) selected.