Image Classification On Stanford Cars

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Vergleichstabelle

Modellname	Accuracy
resmlp-feedforward-networks-for-image	84.6
understanding-gaussian-attention-bias-of	83.89
incorporating-convolution-designs-into-visual	93.2
transboost-improving-the-best-imagenet	90.80%
resmlp-feedforward-networks-for-image	89.5
incorporating-convolution-designs-into-visual	94.1
levit-a-vision-transformer-in-convnet-s	88.4
levit-a-vision-transformer-in-convnet-s	88.2
levit-a-vision-transformer-in-convnet-s	89.3
efficientnetv2-smaller-models-and-faster	94.6
with-a-little-help-from-my-friends-nearest	67.1
global-filter-networks-for-image	93.2
efficientnetv2-smaller-models-and-faster	93.8
incorporating-convolution-designs-into-visual	90.5
stochastic-subsampling-with-average-pooling	85.812
levit-a-vision-transformer-in-convnet-s	88.6
efficientnetv2-smaller-models-and-faster	95.1
domain-adaptive-transfer-learning-on-visual	94.1
going-deeper-with-image-transformers	94.2
imagenet-21k-pretraining-for-the-masses	96.32
incorporating-convolution-designs-into-visual	93
levit-a-vision-transformer-in-convnet-s	89.8
efficient-adaptive-ensembling-for-image	96.879
understanding-gaussian-attention-bias-of	93.743