EfficientNet-B3 (autoaug)

Reported on 6 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology3 results

Domain AdaptationonVizWiz-Classification
Accuracy - All Images· 2018-05-24
42.6
best: 57.2 (VOLO-D5)
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501
Domain AdaptationonVizWiz-Classification
Accuracy - Clean Images· 2018-05-24
47.5
best: 450 (ViT-8/B-224)
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501
Domain AdaptationonVizWiz-Classification
Accuracy - Corrupted Images· 2018-05-24
34.9
best: 51.8 (VOLO-D5)
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501

Computer Vision3 results

Domain GeneralizationonVizWiz-Classification
Accuracy - All Images· 2018-05-24
42.6
best: 57.2 (VOLO-D5)
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501
Domain GeneralizationonVizWiz-Classification
Accuracy - Clean Images· 2018-05-24
47.5
best: 450 (ViT-8/B-224)
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501
Domain GeneralizationonVizWiz-Classification
Accuracy - Corrupted Images· 2018-05-24
34.9
best: 51.8 (VOLO-D5)
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501