Texture Classification on GTOS-Mobile
90.2AccuracyRADAM
Evaluation results
| Method | Links | |
|---|---|---|
| RADAMBackbone=ConvNeXt-XL, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 90.2 | |
| RADAMBackbone=ConvNeXt-L, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 87.3 | |
| RADAMBackbone=ConvNeXt-B, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 87.1 | |
| DSRNetBackbone=ResNet50, Input size=224x2242023.03 | 87 | |
| DFAENBackbone=ResNet50, Input size=224x2242023.03 | 86.9 | |
| DFAENBackbone=Densenet161, Input size=224x2242023.03 | 86.9 | |
| MAPNetBackbone=ResNet50, Input size=224x2242023.03 | 86.6 | |
| RADAMBackbone=ConvNeXt-T, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 86.5 | |
| RADAMBackbone=ConvNeXt-L, Input size=224x2242023.03 | 85.8 | |
| CLASSNetBackbone=ResNet50, Input size=224x2242023.03 | 85.7 | |
| CLASSNetBackbone=ResNet18, Input size=224x2242023.03 | 85.3 | |
| RADAMBackbone=ConvNeXt-T, Input size=224x2242023.03 | 85.3 | |
| DSRNetBackbone=ResNet18, Input size=224x2242023.03 | 83.7 | |
| MAPNetBackbone=ResNet18, Input size=224x2242023.03 | 83 | |
| DEPNetBackbone=ResNet18, Input size=224x2242023.03 | 82.2 | |
| RADAMBackbone=ConvNeXt-B, Input size=224x2242023.03 | 82.2 | |
| RADAMBackbone=ConvNeXt-nano, Input size=224x2242023.03 | 81.8 | |
| RADAMBackbone=ResNet50, Input size=224x2242023.03 | 81 | |
| RADAMBackbone=ResNet18, Input size=224x2242023.03 | 79.5 | |
| RADAM lightBackbone=MobileNet V2 1.4, Input size=224x2242023.03 | 78.2 | |
| DeepTENBackbone=ResNet18, Input size=352x3522023.03 | 76.1 | |
| RADAM lightBackbone=MobileNet V2, Input size=224x2242023.03 | 75.1 |