Image Classification on Oxford IIIT Pets (Top-1 Error Rate)
2.9Top-1 Error RateEfficientNet-L2
Evaluation results
| Method | Links | |
|---|---|---|
| EfficientNet-L2Backbone=EfficientNet-L2, SAM Optimization=true, Pre-training Dataset=ImageNet plus JFT2020.10 | 2.9 | |
| EfficientNet-L2Backbone=EfficientNet-L2, SAM Optimization=false, Pre-training Dataset=ImageNet plus JFT2020.10 | 3.08 | |
| EfficientNet-b7Backbone=EfficientNet-b7, SAM Optimization=true, Pre-training Dataset=ImageNet-only2020.10 | 3.97 | |
| Gpipe2020.10 | 4.1 | |
| EfficientNet-b7Backbone=EfficientNet-b7, SAM Optimization=false, Pre-training Dataset=ImageNet-only2020.10 | 4.24 |