Object Detection on NYU Depth v2 (test)
55.4mAPRBF Weighted Hyper-Involution
Evaluation results
| Method | Links | |
|---|---|---|
| RBF Weighted Hyper-InvolutionInput modality=RGB-D, RGB backbone=YOLO, Depth backbone=Depth-aware Modulation2023.09 | 55.4 | |
| MCTNetInput modality=RGB-D, RGB backbone=ResNet-50, Depth backbone=ResNet-182023.09 | 54.8 | |
| FetNetInput modality=RGB-D, RGB backbone=ResNet-50, Depth backbone=ResNet-1522023.09 | 54 | |
| CMACInput modality=RGB-D, RGB backbone=VGG-16, Depth backbone=AlexNet2023.09 | 52.3 | |
| AC-CNNInput modality=RGB-D, RGB backbone=VGG-16, Depth backbone=AlexNet2023.09 | 50.2 | |
| Faster R-CNNInput modality=RGB, RGB backbone=ResNet-50, Depth backbone=-2023.09 | 49.7 | |
| Cascade R-CNNInput modality=RGB, RGB backbone=ResNet-50, Depth backbone=-2023.09 | 49.3 | |
| Dynamic R-CNNInput modality=RGB, RGB backbone=ResNet-50, Depth backbone=-2023.09 | 49.2 | |
| Super TransferInput modality=RGB-D, RGB backbone=VGG-16, Depth backbone=AlexNet2023.09 | 49.1 | |
| SABLInput modality=RGB, RGB backbone=ResNet-50, Depth backbone=-2023.09 | 48.6 | |
| ATSSInput modality=RGB, RGB backbone=ResNet-50, Depth backbone=-2023.09 | 44.4 | |
| GFLInput modality=RGB, RGB backbone=ResNet-50, Depth backbone=-2023.09 | 44.2 | |
| Sparse R-CNNInput modality=RGB, RGB backbone=ResNet-50, Depth backbone=-2023.09 | 40.2 | |
| RGB-D R-CNNInput modality=RGB-D, RGB backbone=AlexNet, Depth backbone=AlexNet2023.09 | 32.5 | |
| YOLOv11Input modality=RGB, RGB backbone=YOLOv11x, Depth backbone=-2023.09 | 21.4 | |
| YOLOv8Input modality=RGB, RGB backbone=YOLOv8x, Depth backbone=-2023.09 | 20.6 | |
| YOLOv12Input modality=RGB, RGB backbone=YOLOv12x, Depth backbone=-2023.09 | 18.9 |