Object Detection on Utokyo
6.5APThermal-Det
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Thermal-DetZero-shot=true, Backbone=Swin-T2026.05 | 6.5 | 13.7 | 5.4 | |
| YOLO-WorldVenue=CVPR’24, Zero-shot=true, Backbone=Swin-T2026.05 | 5 | 10.1 | 4.3 | |
| G-DINOVenue=ECCV’24, Zero-shot=true, Backbone=Swin-T2026.05 | 5 | 9.3 | 16.9 | |
| LLMDetVenue=CVPR’25, Zero-shot=true, Backbone=Swin-T2026.05 | 5 | 10.2 | 4.5 | |
| GLIPVenue=NeurIPS’22, Zero-shot=true, Backbone=Swin-T2026.05 | 4.9 | 9.3 | 4.6 | |
| T-Rex2Venue=ECCV’24, Zero-shot=true, Backbone=Swin-T2026.05 | 4.9 | 10.1 | 4.3 | |
| MM-GDINOZero-shot=true, Backbone=Swin-T2026.05 | 4.7 | 9.5 | 4.2 | |
| G-DINOSetup=Fine-tuning (FT), Backbone=Swin-T2026.05 | 0.129 | 0.252 | 0.115 | |
| Thermal-DetSetup=Zero-shot, Backbone=Swin-T, Pre-training=Synthetic GroundingCap-1M, M3FD, MMPD, MS22026.05 | 0.065 | 0.137 | 0.054 | |
| YOLO-WorldSetup=Zero-shot, Backbone=YOLOv8-L, Pre-training=O365, GoldG, CC3M2026.05 | 0.05 | 0.101 | 0.043 | |
| G-DINOSetup=Zero-shot, Backbone=Swin-T, Pre-training=O365, GoldG, Cap4M2026.05 | 0.05 | 0.093 | 0.169 | |
| LLMDetSetup=Zero-shot, Backbone=Swin-T, Pre-training=GroundingCap-1M2026.05 | 0.05 | 0.102 | 0.045 | |
| GLIPSetup=Zero-shot, Backbone=Swin-T, Pre-training=O365, GoldG, Cap4M2026.05 | 0.049 | 0.093 | 0.046 | |
| T-Rex2Setup=Zero-shot, Backbone=Swin-T, Pre-training=10M data from various resources2026.05 | 0.049 | 0.101 | 0.043 | |
| MM-GDINOSetup=Zero-shot, Backbone=Swin-T, Pre-training=O365, GoldG, GRIT, V3Det2026.05 | 0.047 | 0.095 | 0.042 |