Regression on FryNet (test)
2.66PVFryNet
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| FryNetBackbone=MiT-B2, Params=31.0M, GFLOPs=30.3, FPS=47.1, Modality=RGB + thermal2026.04 | 2.66 | 1.98 | 2.86 | 1.8 | 2.32 | |
| DINOv2Backbone=ViT-B, Params=87.8M, GFLOPs=119.0, FPS=46.4, Modality=thermal only2026.04 | 3.24 | 11.88 | 11.99 | 7.58 | 8.67 | |
| DeepLabV3Backbone=ResNet-50, Params=24.9M, GFLOPs=110.0, FPS=130.0, Modality=thermal only2026.04 | 3.71 | 13.58 | 14.26 | 2.46 | 8.5 | |
| Swin-SBackbone=Swin-S, Params=49.6M, GFLOPs=54.5, FPS=40.4, Modality=thermal only2026.04 | 3.87 | 10.43 | 16.64 | 3.34 | 8.57 | |
| CMNeXtBackbone=MiT-B2×2, Params=58.8M, GFLOPs=74.2, FPS=31.0, Modality=RGB + thermal2026.04 | 4.18 | 10.72 | 10.43 | 6.76 | 8.02 | |
| ConvNeXt-BBackbone=ConvNeXt-B, Params=88.5M, GFLOPs=85.8, FPS=59.0, Modality=thermal only2026.04 | 4.64 | 8.88 | 14.64 | 4.98 | 8.29 | |
| SegFormerBackbone=MiT-B2, Params=24.9M, GFLOPs=25.3, FPS=66.2, Modality=thermal only2026.04 | 4.74 | 6.34 | 14.35 | 4.1 | 7.38 | |
| CMXBackbone=MiT-B2×2, Params=66.7M, GFLOPs=78.3, FPS=31.1, Modality=RGB + thermal2026.04 | 6.41 | 35.93 | 23.25 | 16.92 | 20.62 |