Domain Generalization On Vizwiz

评估指标

Accuracy - All Images
Accuracy - Clean Images
Accuracy - Corrupted Images

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
VOLO-D557.259.751.8VOLO: Vision Outlooker for Visual Recognition
ConvNeXt-B53.55646.9A ConvNet for the 2020s
ResNeXt-101 32x16d51.754.848.1Aggregated Residual Transformations for Deep Neural Networks
EfficientNet-B8 (advprop+autoaug)50.553.245.8Adversarial Examples Improve Image Recognition
EfficientNet-B7 (advprop+autoaug)49.75245Adversarial Examples Improve Image Recognition
EfficientNet-B6 (advprop+autoaug)49.653.244.7Adversarial Examples Improve Image Recognition
EfficientNet-B5 (advprop+autoaug)49.151.744Adversarial Examples Improve Image Recognition
ViT-16/L-22449--An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
ResNet-50 (gn)48.944.439.1ResNet strikes back: An improved training procedure in timm
EfficientNet-B4 (advprop+autoaug)48.151.442.5Adversarial Examples Improve Image Recognition
ResNet-15247.551.343.3Deep Residual Learning for Image Recognition
ResNet-10146.350.140.5Deep Residual Learning for Image Recognition
EfficientNet-B6 (autoaug)45.850.739.3AutoAugment: Learning Augmentation Strategies From Data-
EfficientNet-B5 (autoaug)45.750.239.8AutoAugment: Learning Augmentation Strategies From Data-
EfficientNet-B3 (advprop+autoaug)45.549.539.8Adversarial Examples Improve Image Recognition
EfficientNet-B7 (autoaug)4549.939.1AutoAugment: Learning Augmentation Strategies From Data-
EfficientNet-B7 (randaug)4548.738.9RandAugment: Practical automated data augmentation with a reduced search space
EfficientNet-B4 (autoaug)44.348.638.2AutoAugment: Learning Augmentation Strategies From Data-
EfficientNet-B2 (advprop+autoaug)44.34838.2Adversarial Examples Improve Image Recognition
ResNet-5042.947.737.1Deep Residual Learning for Image Recognition
0 of 90 row(s) selected.
Domain Generalization On Vizwiz | SOTA | HyperAI超神经