Model-based 2D detection of unseen objects – HB

This leaderbord shows the ranking for Model-based 2D detection of unseen objects on HB. 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 0.605 0.768 0.635 0.048 0.613 0.735 0.646 0.656 0.656 0.063 0.651 0.887 0.533
2024-05-08 NIDS-Net_WA RGB 0.594 0.764 0.618 0.045 0.606 0.643 0.643 0.650 0.650 0.046 0.648 0.802 0.467
2024-11-16 MUSE (full) RGB 0.589 0.744 0.619 0.013 0.598 0.688 0.625 0.641 0.641 0.067 0.639 0.853 0.511
2024-05-08 NIDS-Net_WA_Sappe RGB 0.587 0.755 0.609 0.044 0.598 0.665 0.634 0.649 0.649 0.046 0.645 0.850 0.463
2024-09-18 F3DT2D (test01/blenderproc) RGB 0.577 0.721 0.610 0.006 0.586 0.737 0.614 0.626 0.626 0.017 0.624 0.846 0.456
2023-11-23 ViewInvDet RGB 0.554 0.721 0.581 0.001 0.560 0.685 0.616 0.624 0.624 0.017 0.621 0.816 1.719
2023-12-05 SAM6D-FastSAM RGB-D 0.551 0.707 0.573 0.018 0.556 0.727 0.590 0.595 0.595 0.017 0.590 0.826 0.442
2024-05-08 NIDS-Net_basic RGB 0.548 0.700 0.570 0.044 0.558 0.629 0.598 0.613 0.613 0.046 0.609 0.832 0.469
2023-12-05 SAM6D RGB-D 0.530 0.722 0.549 0.006 0.541 0.601 0.575 0.582 0.582 0.043 0.580 0.711 2.957
2024-03-22 SAM6D-FastSAM(RGB) RGB 0.523 0.676 0.544 0.018 0.525 0.680 0.577 0.585 0.585 0.017 0.578 0.822 0.249
2023-08-02 CNOS (FastSAM) (FastSAM) RGB 0.517 0.669 0.532 0.006 0.523 0.658 0.578 0.586 0.586 0.017 0.579 0.826 0.220
2023-08-02 CNOS (SAM) (SAM) RGB 0.423 0.565 0.440 0.005 0.435 0.386 0.475 0.479 0.479 0.043 0.477 0.522 1.803
2023-09-17 ZeroPose RGB 0.398 0.547 0.397 0.000 0.419 0.431 0.492 0.525 0.525 0.003 0.531 0.638 3.628

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

Latest submissions to this leaderboard: