List your company

Image Classification on ImageNet-ES (test)

98.5Oracle (S)OpenCLIP-h
92.15693.80395.4597.097Mar 4, 2025

Evaluation results

MethodLinks
OpenCLIP-hNum. Params=632M, Pretraining Dataset=LAION-2B, DG method=Text-guided pretrain2025.0398.587.17977.693—
DINOv2-gNum. Params=1.1B, Pretraining Dataset=LVD-142M, DG method=Dataset curation2025.039890.784.379.893.1—
DINOv2-bNum. Params=90M, Pretraining Dataset=LVD-142M, DG method=Dataset curation2025.0397.685.174.573.990.6—
OpenCLIP-bNum. Params=87M, Pretraining Dataset=LAION-2B, DG method=Text-guided pretrain2025.0397.481.466.171.390.9—
SwinV2-SNum. Params=50M, Pretraining Dataset=IN-1K, DG method=-2025.0395.474.459.965.584.5—
SwinV2-BNum. Params=88M, Pretraining Dataset=IN-1K, DG method=-2025.0395.375.36065.585.3—
SwinV2-TNum. Params=28M, Pretraining Dataset=IN-1K, DG method=-2025.0395.170.454.163.182.6—
EfficientNet-B3Num. Params=12M, Pretraining Dataset=IN-1K, DG method=-2025.0394.873.96266.383.5—
EfficientNet-B0Num. Params=5M, Pretraining Dataset=IN-1K, DG method=-2025.0394.168.251.858.381.2—
ResNet-152Num. Params=60M, Pretraining Dataset=IN-1K, DG method=-2025.0393.658.241.154.381.1—
ResNet-50Num. Params=26M, Pretraining Dataset=IN-21K, DG method=DeepAugment*+AugMix†2025.039366.953.261.483.1—
ResNet-50Num. Params=26M, Pretraining Dataset=IN-1K, DG method=-2025.0392.449.532.150.478.6—
SNNArchitecture=ResNet18+LIF, Mode=baseline2025.11—————39.89
SNNArchitecture=ResNet18+LIF, Mode=pre-train2025.11—————43.74
SNNArchitecture=ResNet18+LIAF, Mode=pre-train2025.11—————52.25
SNNArchitecture=ResNet34+LIF, Mode=baseline2025.11—————43.42
SNNArchitecture=ResNet34+LIAF, Mode=pre-train2025.11—————51.83