Domain Generalization On Imagenet Sketch
المقاييس
Top-1 accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Top-1 accuracy |
|---|---|
| model-soups-averaging-weights-of-multiple | 74.24 |
| pyramid-adversarial-training-improves-vit | 41.04 |
| masked-autoencoders-are-scalable-vision | 50.9 |
| metaformer-baselines-for-vision | 54.5 |
| metaformer-baselines-for-vision | 52.9 |
| pyramid-adversarial-training-improves-vit | 46.03 |
| metaformer-baselines-for-vision | 42.5 |
| enhance-the-visual-representation-via | 50.03 |
| metaformer-baselines-for-vision | 39.5 |
| distilling-out-of-distribution-robustness-1 | 46.1 |
| model-soups-averaging-weights-of-multiple | 77.18 |
| metaformer-baselines-for-vision | 52.8 |
| metaformer-baselines-for-vision | 52.7 |
| generalized-parametric-contrastive-learning | 48.3 |
| sequencer-deep-lstm-for-image-classification | 35.8 |
| context-aware-robust-fine-tuning | 65.5 |
| vision-models-are-more-robust-and-fair-when | 45.6 |
| discrete-representations-strengthen-vision-1 | 44.72 |
| a-convnet-for-the-2020s | 55.0 |
| a-whac-a-mole-dilemma-shortcuts-come-in | 53.39 |