Image Classification (Top-K Accuracy) on CIFAR-100 (test)
23.15Top-1 AccCyCLIP
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 | 23.15 | 41.46 | 50.66 | |
| CLIPEvaluation Mode=Zero-shot, Prompt engineering=true, Image Encoder=ResNet-50, Text Encoder=Transformer, Pre-training Data=CC3M2022.05 | 18.69 | 34.72 | 43.97 |