Object Counting
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.
Source: Learning to Count Objects with Few Exemplar Annotations
Papers
Showing 1–10 of 158 papers
All datasetsFSC147CARPKPascal VOC 2007 count-testCOCO count-testTallyQA-ComplexTallyQA-SimpleHowMany-QAPASCAL VOCOmnicount-191TRANCOS
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FamNet | MAE(test) | 22.08 | — | Unverified |
| 2 | Omnicount (Open vocabulary, multi-label, without training) | MAE(test) | 18.63 | — | Unverified |
| 3 | RCC | MAE(test) | 17.12 | — | Unverified |
| 4 | Counting-DETR | MAE(test) | 16.79 | — | Unverified |
| 5 | CounTX (uses text descriptions instead of visual exemplars) | MAE(test) | 15.88 | — | Unverified |
| 6 | LaoNet | MAE(test) | 15.78 | — | Unverified |
| 7 | BMNet+ | MAE(test) | 14.62 | — | Unverified |
| 8 | SAFECount | MAE(test) | 14.32 | — | Unverified |
| 9 | GCA-SUN | MAE(test) | 14 | — | Unverified |
| 10 | SPDCN | MAE(test) | 13.51 | — | Unverified |