Visual Explanation on MS-COCO (Ins/Del/OA Metrics)
38.72Insertion Score (Class)EIVE
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| EIVEDetector=Deformable-DETR, Time (s)=0.07632026.06 | 38.72 | — | — | — | 32.08 | 47.65 | 16.15 | 99.56 | 91.63 | 0.5115 | |
| EIVEDetector=DINO, Time (s)=0.07762026.06 | 31.79 | — | — | — | 32.21 | 44.59 | 15.59 | 72.63 | 75.91 | 0.9727 | |
| VPSDetector=Deformable-DETR, Time (s)=110.94042026.06 | 31.02 | — | — | — | 31.39 | 25.49 | 15.3 | 33.24 | 21.33 | 6.9094 | |
| VPSDetector=DINO, Time (s)=118.32572026.06 | 28.08 | — | — | — | 31.67 | 28.72 | 15.91 | 34.98 | 25.09 | 5.9937 | |
| ODAMDetector=DINO, Time (s)=0.25422026.06 | 27.8 | — | — | — | 32.48 | 37.77 | 17.88 | 81.92 | 34.68 | 4.2415 | |
| ODAMDetector=Deformable-DETR, Time (s)=0.22962026.06 | 27.25 | — | — | — | 33.21 | 28.65 | 18.1 | 75.06 | 30.1 | 4.7976 | |
| D-RISEDetector=Deformable-DETR, Time (s)=42.42132026.06 | 26.99 | — | — | — | 31.95 | 27.49 | 16.39 | 68.96 | 10.1 | 7.3167 | |
| D-RISEDetector=DINO, Time (s)=55.69822026.06 | 24.64 | — | — | — | 31.92 | 32.69 | 16.57 | 72.02 | 11.1 | 6.605 | |
| VPSDetector=DETR, Time (s)=62.97092026.06 | 23.82 | — | — | — | 79.59 | 23.07 | 73.49 | 27.69 | 17.26 | 7.6499 | |
| EIVEDetector=DETR, Time (s)=0.04402026.06 | 22.87 | — | — | — | 72.95 | 24.44 | 68.81 | 84.75 | 77.36 | 0.8389 | |
| EIVEDetector=Conditional-DETR, Time (s)=0.05122026.06 | 22.35 | — | — | — | 29.7 | 8.81 | 11.52 | 88.72 | 79.52 | 0.8778 | |
| VPSDetector=Conditional-DETR, Time (s)=66.11612026.06 | 20.57 | — | — | — | 29.77 | 7.78 | 11.2 | 40.4 | 22.67 | 5.6309 | |
| ODAMDetector=DETR, Time (s)=0.17472026.06 | 17.77 | — | — | — | 76.77 | 19.61 | 74.95 | 59.76 | 25.67 | 5.8981 | |
| D-RISEDetector=DETR, Time (s)=17.99772026.06 | 17.71 | — | — | — | 77.31 | 19.62 | 73.36 | 59.31 | 9.44 | 7.7725 | |
| ODAMDetector=Conditional-DETR, Time (s)=0.17322026.06 | 17.04 | — | — | — | 29 | 7.27 | 11.63 | 77.42 | 34.98 | 4.2487 | |
| D-RISEDetector=Conditional-DETR, Time (s)=30.08252026.06 | 15.71 | — | — | — | 29.38 | 6.87 | 11.62 | 73.53 | 11.6 | 5.96 | |
| GradCAM++Detector=DETR, Time (s)=0.17342026.06 | 14.86 | — | — | — | 91.58 | 15.29 | 92.46 | 19.23 | 13.43 | 7.0832 | |
| GradCAM++Detector=DINO, Time (s)=0.24462026.06 | 12.19 | — | — | — | 44.65 | 8.95 | 30.27 | 25.3 | 15.41 | 6.1136 | |
| GradCAM++Detector=Deformable-DETR, Time (s)=0.22612026.06 | 11.96 | — | — | — | 43 | 6.99 | 27.59 | 23 | 13.92 | 6.7856 | |
| GradCAM++Detector=Conditional-DETR, Time (s)=0.17082026.06 | 10.93 | — | — | — | 31.87 | 4.52 | 12.29 | 19.11 | 15.34 | 6.0054 | |
| GradCAMDetector=DETR, Time (s)=0.16622026.06 | 9.75 | — | — | — | 96.6 | 10.42 | 95.87 | 13.46 | 10.82 | 7.8037 | |
| GradCAMDetector=Deformable-DETR, Time (s)=0.19992026.06 | 8.69 | — | — | — | 46.39 | 5.11 | 28.13 | 20.14 | 13.26 | 6.5896 | |
| GradCAMDetector=DINO, Time (s)=0.22142026.06 | 7.54 | — | — | — | 49.49 | 6.32 | 31.14 | 20.99 | 13.76 | 6.0639 | |
| GradCAMDetector=Conditional-DETR, Time (s)=0.16852026.06 | 7.36 | — | — | — | 34.45 | 3.93 | 11.7 | 18.67 | 13.31 | 6.0099 | |
| VPSDetector=DAB-DETR, Time (s)=69.20422026.06 | 6.08 | — | — | — | 17.42 | 1.93 | 8 | 34.52 | 22.58 | 5.8409 | |
| EIVEDetector=DAB-DETR, Time (s)=0.04992026.06 | 5.5 | — | — | — | 17.99 | 2.71 | 8.05 | 90.47 | 81.2 | 1.2089 | |
| D-RISEDetector=DAB-DETR, Time (s)=29.05992026.06 | 4.6 | — | — | — | 17.28 | 2.37 | 8.05 | 71.69 | 11.36 | 6.3754 | |
| ODAMDetector=DAB-DETR, Time (s)=0.17352026.06 | 4.49 | — | — | — | 17.43 | 2.1 | 8.14 | 68.29 | 32.1 | 4.5818 | |
| GradCAM++Detector=DAB-DETR, Time (s)=0.16872026.06 | 3.29 | — | — | — | 18.79 | 0.74 | 8.61 | 13.68 | 14.77 | 6.6473 | |
| GradCAMDetector=DAB-DETR, Time (s)=0.16292026.06 | 2.69 | — | — | — | 19.56 | 0.68 | 8.45 | 15.66 | 14.46 | 6.2886 | |
| VPSBase Model=Grounding DINO2024.12 | — | 94.6 | 30 | 64.6 | — | — | — | — | — | — | |
| VX-CODEBase Model=Grounding DINO, r=12024.12 | — | 96.2 | 21.1 | 75.1 | — | — | — | — | — | — |