Image Classification on ImageNet-C Average of 15 corruptions (test)
44.8Top-1 AccRELICv2
Evaluation results
| Method | Links | |
|---|---|---|
| RELICv2Protocol=Linear evaluation, Backbone=ResNet-50, Pre-training=ImageNet, Evaluation=Zero-shot2022.01 | 44.8 | |
| RELICProtocol=Linear evaluation, Backbone=ResNet-50, Pre-training=ImageNet, Evaluation=Zero-shot2022.01 | 44.5 | |
| BYOLProtocol=Linear evaluation, Backbone=ResNet-50, Pre-training=ImageNet, Evaluation=Zero-shot2022.01 | 42.8 | |
| SupervisedProtocol=Linear evaluation, Backbone=ResNet-50, Pre-training=ImageNet, Evaluation=Zero-shot2022.01 | 40.9 | |
| SimCLRProtocol=Linear evaluation, Backbone=ResNet-50, Pre-training=ImageNet, Evaluation=Zero-shot2022.01 | 31.1 |