List your company
ResearchFormerly WizWand

Image Classification on ImageNet-A 1.0 (val)

74.5Top-1 AccFAN-L-Hybrid
-2.9817.13537.2557.365May 17, 2021Jul 13, 2021Sep 8, 2021Nov 5, 2021Jan 1, 2022Feb 27, 2022Apr 26, 2022
Updated 8mo ago

Evaluation results

MethodLinks
FAN-L-HybridParams (M)=76.8, Pre-trained=ImageNet-22K, Resolution=384x3842022.0474.5
ConvNeXt-XLData/Size=22K/384^2, FLOPs (G)=179, Params (M)=350.22022.0169.3
ConvNeXt-LData/Size=22K/384^2, FLOPs (G)=101, Params (M)=197.82022.0165.5
ConvNeXt-BData/Size=22K/384^2, FLOPs (G)=45.1, Params (M)=88.62022.0162.3
ConvNeXt-BParams (M)=88.6, Pre-trained=ImageNet-22K, Resolution=384x3842022.0462.3
FAN-L-HybridParams (M)=76.8, Pre-trained=ImageNet-22K, Resolution=224x2242022.0460.7
MAE-VIT-LParams (M)=307, Pre-trained=ImageNet-1K, Resolution=224x2242022.0457.1
RVT-B*Pre-training=ImageNet-22K, Fine-tuning=ImageNet-1K2021.0542.27
FAN-L-HybridParams (M)=76.8, Pre-trained=ImageNet-1K, Resolution=224x2242022.0441.8
RVT-BPre-training=ImageNet-22K, Fine-tuning=ImageNet-1K2021.0541
FAN-B-HybridParams (M)=50.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.0439.6
DeiT-BPre-training=ImageNet-22K, Fine-tuning=ImageNet-1K2021.0538.01
FAN-L-VITParams (M)=80.5, Pre-trained=ImageNet-1K, Resolution=224x2242022.0437.2
ConvNeXt-BData/Size=1K/224^2, FLOPs (G)=15.4, Params (M)=88.62022.0136.7
ConvNeXt-BParams (M)=88.6, Pre-trained=ImageNet-1K, Resolution=224x2242022.0436.7
MAE-VIT-BParams (M)=86, Pre-trained=ImageNet-1K, Resolution=224x2242022.0435.9
Swin-BData/Size=1K/224^2, FLOPs (G)=15.4, Params (M)=87.82022.0135.8
Swin-SParams (M)=50, Pre-trained=ImageNet-1K, Resolution=224x2242022.0435.8
Swin-BParams (M)=87.8, Pre-trained=ImageNet-1K, Resolution=224x2242022.0435.8
FAN-B-VITParams (M)=54.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.0435.4
FAN-S-HybridParams (M)=26.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.0433.9
ConvNeXt-SParams (M)=50.2, Pre-trained=ImageNet-1K, Resolution=224x2242022.0431.2
FAN-S-ViTParams (M)=28.0, Pre-trained=ImageNet-1K, Resolution=224x2242022.0429.1
RVT-B*Data/Size=1K/224^2, FLOPs (G)=17.7, Params (M)=91.82022.0128.5
RVT-B*Params (M)=91.8, Pre-trained=ImageNet-1K, Resolution=224x2242022.0428.5
XCiT-S24Params (M)=47.7, Pre-trained=ImageNet-1K, Resolution=224x2242022.0427.8
RVT-S*Data/Size=1K/224^2, FLOPs (G)=4.7, Params (M)=23.32022.0125.7
RVT-S*Params (M)=23.3, Pre-trained=ImageNet-1K, Resolution=224x2242022.0425.7
XCIT-S12Params (M)=26.3, Pre-trained=ImageNet-1K, Resolution=224x2242022.0425
ConvNeXt-TData/Size=1K/224^2, FLOPs (G)=4.5, Params (M)=28.62022.0124.2
ConvNeXt-TParams (M)=28.6, Pre-trained=ImageNet-1K, Resolution=224x2242022.0424.2
Swin-TData/Size=1K/224^2, FLOPs (G)=4.5, Params (M)=28.32022.0121.6
Swin-TParams (M)=28.3, Pre-trained=ImageNet-1K, Resolution=224x2242022.0421.6
ResNet-50Data/Size=1K/224^2, FLOPs (G)=4.1, Params (M)=25.62022.010