Domain Generalization On Imagenet A

المقاييس

Top-1 accuracy %

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

جدول المقارنة

اسم النموذج	Top-1 accuracy %
distilling-out-of-distribution-robustness-1	7.7
cutmix-regularization-strategy-to-train	7.3
rethinking-the-design-principles-of-robust	14.4
rethinking-the-design-principles-of-robust	25.7
improved-regularization-of-convolutional	4.4
natural-adversarial-examples	0
a-continual-development-methodology-for-large	84.53
metaformer-baselines-for-vision	69.4
masked-autoencoders-are-scalable-vision	76.7
metaformer-baselines-for-vision	48.5
understanding-the-robustness-in-vision	74.5
deep-residual-learning-for-image-recognition	4.2
model-soups-averaging-weights-of-multiple	94.17
fully-attentional-networks-with-self-emerging-1	46.1
transnext-robust-foveal-visual-perception-for	50.6
metaformer-baselines-for-vision	79.5
model-soups-averaging-weights-of-multiple	92.67
on-feature-normalization-and-data	8.4
imagenet-trained-cnns-are-biased-towards	2.3
metaformer-baselines-for-vision	55.3
enhance-the-visual-representation-via	68.92
pyramid-adversarial-training-improves-vit	36.41
mixup-beyond-empirical-risk-minimization	6.6
pyramid-adversarial-training-improves-vit	62.44
your-diffusion-model-is-secretly-a-zero-shot	30.2
context-aware-robust-fine-tuning	81.5
rethinking-the-design-principles-of-robust	28.5
metaformer-baselines-for-vision	63.3
vision-models-are-more-robust-and-fair-when	52.7
transnext-robust-foveal-visual-perception-for	47.1
sequencer-deep-lstm-for-image-classification	35.5
distilling-out-of-distribution-robustness-1	31.8
metaformer-baselines-for-vision	61.9
global-filter-networks-for-image	14.3
metaformer-baselines-for-vision	73.5
metaformer-baselines-for-vision	40.1
transnext-robust-foveal-visual-perception-for	58.3
a-convnet-for-the-2020s	69.3
transnext-robust-foveal-visual-perception-for	61.6