Image Classification on ImageNet-C 1.0 (val) (Corruption Error)
27.1Corruption ErrorConvNeXt-XL
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ConvNeXt-XLData/Size=22K/384^2, FLOPs (G)=179, Params (M)=350.22022.01 | 27.1 | — | |
| ConvNeXt-LData/Size=22K/384^2, FLOPs (G)=101, Params (M)=197.82022.01 | 29.9 | — | |
| ConvNeXt-BData/Size=22K/384^2, FLOPs (G)=45.1, Params (M)=88.62022.01 | 30.7 | — | |
| GPaCoModel=ViT-L, Mixup and CutMix=w/o Mixup and CutMix2022.09 | 30.7 | 39 | |
| RVT-B*Data/Size=1K/224^2, FLOPs (G)=17.7, Params (M)=91.82022.01 | 30.8 | — | |
| MAEModel=ViT-L, Mixup and CutMix=w/ Mixup and CutMix2022.09 | 32.4 | 41.4 | |
| ConvNeXt-BData/Size=1K/224^2, FLOPs (G)=15.4, Params (M)=88.62022.01 | 34.4 | — | |
| FAN-L-HybridParams (M)=76.8, Pre-trained=ImageNet-22K, Resolution=224x2242022.04 | 35.8 | — | |
| FAN-L-HybridParams (M)=76.8, Pre-trained=ImageNet-22K, Resolution=384x3842022.04 | 36 | — | |
| MAEModel=ViT-L, Mixup and CutMix=w/o Mixup and CutMix2022.09 | 36.4 | 46.3 | |
| GPaCoModel=ViT-B, Mixup and CutMix=w/o Mixup and CutMix2022.09 | 37.2 | 47.3 | |
| RVT-S*Data/Size=1K/224^2, FLOPs (G)=4.7, Params (M)=23.32022.01 | 37.5 | — | |
| MAEModel=ViT-B, Mixup and CutMix=w/ Mixup and CutMix2022.09 | 39.1 | 49.9 | |
| ConvNeXt-TData/Size=1K/224^2, FLOPs (G)=4.5, Params (M)=28.62022.01 | 40 | — | |
| MAE-VIT-LParams (M)=307, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 41.8 | — | |
| RVT-B*Pre-training=ImageNet-22K, Fine-tuning=ImageNet-1K2021.05 | 42.99 | — | |
| FAN-L-HybridParams (M)=76.8, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 43 | — | |
| ConvNeXt-BParams (M)=88.6, Pre-trained=ImageNet-22K, Resolution=384x3842022.04 | 43.1 | — | |
| FAN-L-VITParams (M)=80.5, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 43.3 | — | |
| RVT-BPre-training=ImageNet-22K, Fine-tuning=ImageNet-1K2021.05 | 44.26 | — | |
| FAN-B-VITParams (M)=54.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 44.4 | — | |
| MAEModel=ViT-B, Mixup and CutMix=w/o Mixup and CutMix2022.09 | 44.9 | 56.9 | |
| FAN-B-HybridParams (M)=50.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 45.2 | — | |
| DeiT-BPre-training=ImageNet-22K, Fine-tuning=ImageNet-1K2021.05 | 45.5 | — | |
| RVT-B*Params (M)=91.8, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 46.8 | — | |
| ConvNeXt-BParams (M)=88.6, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 46.8 | — | |
| FAN-S-ViTParams (M)=28.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 47.7 | — | |
| FAN-S-HybridParams (M)=26.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 47.8 | — | |
| XCiT-S24Params (M)=47.7, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 49.4 | — | |
| GPaCoModel=ResNet-50, Mixup and CutMix=w/o Mixup and CutMix2022.09 | 50.9 | 64.4 | |
| ConvNeXt-SParams (M)=50.2, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 51.2 | — | |
| RVT-S*Params (M)=23.3, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 51.4 | — | |
| XCIT-S12Params (M)=26.3, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 51.5 | — | |
| MAE-VIT-BParams (M)=86, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 51.7 | — | |
| Swin-SParams (M)=50, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 52.7 | — | |
| ConvNeXt-TParams (M)=28.6, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 53.2 | — | |
| Swin-BParams (M)=87.8, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 54.4 | — | |
| ResNet-50Data/Size=1K/224^2, FLOPs (G)=4.1, Params (M)=25.62022.01 | 57.7 | — | |
| Swin-TParams (M)=28.3, Pre-trained=ImageNet-1K, Resolution=224x2242022.04 | 59.6 | — | |
| SupConModel=ResNet-50, Mixup and CutMix=w/o Mixup and CutMix2022.09 | 67.2 | 94.6 |