This leaderbord shows the ranking for Model-based 2D detection of unseen objects on HANDAL. The reported time is the average time to generate predictions for all objects in a single image (averaged over the datasets).
| Date (UTC) | Submission | Test image | AP | AP50 | AP75 | APS | APM | APL | AR1 | AR10 | AR100 | ARS | ARM | ARL | Time (s) | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2025-11-14 | 3PT-Detection (Nov 2025) | RGB | 0.536 | 0.662 | 0.612 | 0.036 | 0.326 | 0.557 | 0.649 | 0.682 | 0.682 | 0.066 | 0.392 | 0.731 | 4.131 | |
| 2025-10-01 | 3PT-Detection (f.k.a IPT) | RGB | 0.527 | 0.647 | 0.602 | 0.027 | 0.312 | 0.550 | 0.639 | 0.660 | 0.660 | 0.046 | 0.358 | 0.713 | 22.089 | |
| 2025-08-26 | MUSE (muse_full) | RGB | 0.357 | 0.451 | 0.384 | 0.001 | 0.145 | 0.410 | 0.450 | 0.465 | 0.465 | 0.001 | 0.155 | 0.546 | 1.038 | |
| 2024-09-23 | CNOS (FastSAM) (Pyrender) | RGB | 0.246 | 0.319 | 0.260 | 0.000 | 0.089 | 0.289 | 0.359 | 0.371 | 0.371 | 0.000 | 0.106 | 0.441 | 0.323 | |
| 2024-09-23 | CNOS (SAM) (Pyrender) | RGB | 0.197 | 0.260 | 0.209 | 0.003 | 0.074 | 0.238 | 0.281 | 0.288 | 0.288 | 0.003 | 0.092 | 0.356 | 1.747 |
Tip: Hover over the numbers to see more decimal places.