Domain Generalization On Imagenet R

المقاييس

Top-1 Error Rate

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

جدول المقارنة

اسم النموذج	Top-1 Error Rate
model-soups-averaging-weights-of-multiple	4.54
generalized-parametric-contrastive-learning	39.7
vision-models-are-more-robust-and-fair-when	43.9
pyramid-adversarial-training-improves-vit	42.16
improving-vision-transformers-by-revisiting	40.3
imagenet-trained-cnns-are-biased-towards	58.5
when-vision-transformers-outperform-resnets	76.5
a-whac-a-mole-dilemma-shortcuts-come-in	31.3
model-soups-averaging-weights-of-multiple	3.90
masked-autoencoders-are-scalable-vision	33.5
prime-a-few-primitives-can-boost-robustness	53.7
metaformer-baselines-for-vision	48.9
context-aware-robust-fine-tuning	10.3
metaformer-baselines-for-vision	47.8
a-convnet-for-the-2020s	31.8
when-vision-transformers-outperform-resnets	71.9
understanding-the-robustness-in-vision	28.9
rethinking-the-design-principles-of-robust	56.1
rethinking-the-design-principles-of-robust	52.3
metaformer-baselines-for-vision	33.5
when-vision-transformers-outperform-resnets	73.6
metaformer-baselines-for-vision	46.1
sequencer-deep-lstm-for-image-classification	51.9
a-whac-a-mole-dilemma-shortcuts-come-in	33.1
metaformer-baselines-for-vision	45
deep-residual-learning-for-image-recognition	63.9
augmix-a-simple-data-processing-method-to	58.9
the-many-faces-of-robustness-a-critical	57.8
pyramid-adversarial-training-improves-vit	46.08
discrete-representations-strengthen-vision-1	44.74
metaformer-baselines-for-vision	31.7
distilling-out-of-distribution-robustness-1	34.9
enhance-the-visual-representation-via	34.39
metaformer-baselines-for-vision	29.6
rethinking-the-design-principles-of-robust	51.3
fully-attentional-networks-with-self-emerging-1	43.4
the-many-faces-of-robustness-a-critical	53.2
prime-a-few-primitives-can-boost-robustness	57.1
metaformer-baselines-for-vision	34.7