Object Detection On Ua Detrac
評価指標
mAP
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | mAP | Paper Title | Repository |
|---|---|---|---|
| CenterNet | 83.48 | Objects as Points | |
| Faster R-CNN | 58.45 | Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | |
| FFAVOD-SpotNet with U-Net | 88.10 | FFAVOD: Feature Fusion Architecture for Video Object Detection | |
| YOLOv2 | 57.72 | YOLO9000: Better, Faster, Stronger | |
| 3D-DETNet | 53.30 | 3D-DETNet: a Single Stage Video-Based Vehicle Detector | - |
| VSTAM | 90.39 | Video Sparse Transformer With Attention-Guided Memory for Video Object Detection | |
| R-FCN | 69.87 | R-FCN: Object Detection via Region-based Fully Convolutional Networks | |
| SpotNet | 86.8 | SpotNet: Self-Attention Multi-Task Network for Object Detection | |
| RN-VID | 70.57 | RN-VID: A Feature Fusion Architecture for Video Object Detection |
0 of 9 row(s) selected.