Model-based 2D detection of unseen objects – HOPEv2

This leaderbord shows the ranking for Model-based 2D detection of unseen objects on HOPEv2. 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)
2025-03-07 anonymity (.) RGB 0.484 0.671 0.527 0.100 0.119 0.555 0.502 0.566 0.566 0.100 0.151 0.648 1.118
2024-11-17 MUSE (full) RGB 0.474 0.652 0.519 0.100 0.109 0.547 0.488 0.554 0.554 0.100 0.138 0.637 1.536
2024-09-10 CNOS (SAM) (Pyrender) RGB 0.365 0.590 0.388 0.089 0.072 0.419 0.406 0.453 0.453 0.089 0.101 0.521 2.345
2024-09-19 CNOS (FastSAM) (Pyrender) RGB 0.313 0.502 0.320 0.089 0.040 0.361 0.368 0.430 0.430 0.089 0.092 0.491 0.421

Tip: Hover over the numbers to see more decimal places.

Latest submissions to this leaderboard: