Image Classification on SUN397 (first split)
66.2AccuracyReLICv2
Evaluation Results
| Method | Links | |
|---|---|---|
| ReLICv2Evaluation protocol=Linear evaluation, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 66.2 | |
| ReLICv2Evaluation protocol=Fine-tuned, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 64.7 | |
| Supervised-INEvaluation protocol=Fine-tuned, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 64.3 | |
| BYOLEvaluation protocol=Fine-tuned, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 63.7 | |
| SimCLREvaluation protocol=Fine-tuned, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 63.5 | |
| NNCLREvaluation protocol=Linear evaluation, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 62.5 | |
| BYOLEvaluation protocol=Linear evaluation, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 62.2 | |
| Supervised-INEvaluation protocol=Linear evaluation, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 61.9 | |
| SimCLREvaluation protocol=Linear evaluation, Backbone=ResNet-50, Pre-trained=ImageNet2022.01 | 58.8 | |
| Random InitEvaluation protocol=Fine-tuned, Backbone=ResNet-50, Pre-trained=None2022.01 | 53.6 |