Image Classification on CIFAR-10 (test) (Top-K Accuracy)
51.45Top-1 AccuracyCyCLIP
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| CyCLIPEvaluation Mode=Zero-shot, Prompt engineering=true, Image Encoder=ResNet-50, Text Encoder=Transformer, Pre-training Data=CC3M, lambda_1=0.25, lambda_2=0.252022.05 | 51.45 | 79.57 | 91.8 | |
| CLIPEvaluation Mode=Zero-shot, Prompt engineering=true, Image Encoder=ResNet-50, Text Encoder=Transformer, Pre-training Data=CC3M2022.05 | 46.54 | 78.22 | 91.16 |