Image Classification On Oxford Iiit Pets 1
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| CeiT-T (384 finetune resolution) | 94.5 | Incorporating Convolution Designs into Visual Transformers | |
| CvT-W24 | 94.73 | CvT: Introducing Convolutions to Vision Transformers | |
| CeiT-T | 93.8 | Incorporating Convolution Designs into Visual Transformers | |
| CeiT-S | 94.6 | Incorporating Convolution Designs into Visual Transformers | |
| CeiT-S (384 finetune resolution) | 94.9 | Incorporating Convolution Designs into Visual Transformers | |
| Diffusion Classifier (zero-shot) | - | Your Diffusion Model is Secretly a Zero-Shot Classifier |
0 of 6 row(s) selected.