Texture Classification on KTH 2-b
94.4AccuracyRADAM
Evaluation results
| Method | Links | |
|---|---|---|
| RADAMBackbone=ConvNeXt-XL, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 94.4 | |
| FVAE2026.05 | 92.7 | |
| FCFVAE2026.05 | 92.3 | |
| RADAMBackbone=ConvNeXt-B, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 91.8 | |
| RADAMBackbone=ConvNeXt-L, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 91.3 | |
| RankGP-3M-CNN++Backbone=(3 backbones), Input size=224x2242023.03 | 91.1 | |
| RADAMBackbone=ConvNeXt-T, Input size=224x224, Pre-training dataset=ImageNet-21K2023.03 | 91 | |
| RADAMBackbone=ConvNeXt-T, Input size=224x2242023.03 | 90.7 | |
| RADAM2026.05 | 90.7 | |
| RADAMBackbone=ConvNeXt-nano, Input size=224x2242023.03 | 89.6 | |
| RADAMBackbone=ConvNeXt-L, Input size=224x2242023.03 | 89.3 | |
| RADAMBackbone=ResNet50, Input size=224x2242023.03 | 88.5 | |
| FENet2026.05 | 88.2 | |
| CLASSNetBackbone=ResNet50, Input size=224x2242023.03 | 87.7 | |
| RADAMBackbone=ConvNeXt-B, Input size=224x2242023.03 | 87.7 | |
| CLASSNet2026.05 | 87.7 | |
| EfficientNet-B5training_mode=fine-tuning2026.05 | 87 | |
| RADAM lightBackbone=MobileNet V2 1.4, Input size=224x2242023.03 | 86.8 | |
| DFAENBackbone=Densenet161, Input size=224x2242023.03 | 86.6 | |
| DFAEN2026.05 | 86.6 | |
| DFAENBackbone=ResNet50, Input size=224x2242023.03 | 86.3 | |
| DSRNetBackbone=ResNet50, Input size=224x2242023.03 | 85.9 | |
| DSRNet2026.05 | 85.9 | |
| CLASSNetBackbone=ResNet18, Input size=224x2242023.03 | 85.4 | |
| RADAM lightBackbone=MobileNet V2, Input size=224x2242023.03 | 84.8 | |
| RADAMBackbone=ResNet18, Input size=224x2242023.03 | 84.7 | |
| MAPNetBackbone=ResNet50, Input size=224x2242023.03 | 84.5 | |
| Non-Add Entropy2026.05 | 84.4 | |
| Multilayer-FVBackbone=EfficientNet-B5, Input size=512x5122023.03 | 82.9 | |
| LFV2026.05 | 82.6 | |
| DeepTENBackbone=ResNet50, Input size=352x3522023.03 | 82 | |
| DeepTEN2026.05 | 82 | |
| DSRNetBackbone=ResNet18, Input size=224x2242023.03 | 81.8 | |
| FV-VGGVD2026.05 | 81.8 | |
| SIFT-FV2026.05 | 81.5 | |
| MAPNetBackbone=ResNet18, Input size=224x2242023.03 | 80.9 | |
| Capsule2026.05 | 71.8 |