List your company
ResearchFormerly WizWand

Image Classification on CIFAR-100 5-shot (test)

85.2Top-1 AccEVA
26.991242.103157.21572.3269Nov 11, 2024Nov 29, 2024Dec 17, 2024Jan 5, 2025Jan 23, 2025Feb 10, 2025Mar 1, 2025
Updated 8mo ago

Evaluation results

MethodLinks
EVAModel=BEIT-L/14, Pre-training Dataset=CLIP OpenAI, IN-22K, IN-1K, Evaluation Protocol=Linear Probing2024.1185.2
SABackbone=ViT-Large, Shot-count=5-shot2025.0381.98
Split LearningBackbone=ViT-Large, Shot-count=5-shot2025.0379.63
Linear ProbingBackbone=ViT-Large, Shot-count=5-shot2025.0378.79
SABackbone=Swin-L2025.0376.66
Linear ProbingBackbone=Swin-L2025.0375.76
Fine TuningBackbone=Swin-L2025.0373.05
Offsite TuningBackbone=Swin-L2025.0372.8
CLIPModel=ViT-B/16, Pre-training Dataset=LAION-300M, Evaluation Protocol=Linear Probing2024.1171.96
ScaleKDModel=ViT-B/16, Pre-training Dataset=IN-1K, Evaluation Protocol=Linear Probing2024.1170.91
CLIPModel=ViT-B/16, Pre-training Dataset=CLIP OpenAI, IN-12K, IN-1K, Evaluation Protocol=Linear Probing2024.1170.85
CLIPModel=ViT-B/16, Pre-training Dataset=LAION-2B, IN-12K, IN-1K, Evaluation Protocol=Linear Probing2024.1170.19
CLIPModel=ViT-B/16, Pre-training Dataset=LAION-2B, IN-1K, Evaluation Protocol=Linear Probing2024.1169
Split LearningBackbone=Swin-L2025.0365.37
Offsite TuningBackbone=ViT-Large, Shot-count=5-shot2025.0364.83
Fine TuningBackbone=ViT-Large, Shot-count=5-shot2025.0364.29
From-scratchModel=ViT-B/16, Pre-training Dataset=IN-1K, Evaluation Protocol=Linear Probing2024.1160.3
LN-TUNEBackbone=ViT-Large, Shot-count=5-shot2025.0334.8
LN-TUNEBackbone=Swin-L2025.0329.23