AutoAugment

Reported on 2 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision2 results

Image ClassificationonFGVC Aircraft
Top-1 Error Rate· 2018-05-24
7.33
best: 4.82 (EffNet-L2 (SAM))
SOTA
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501
Fine-Grained Image ClassificationonFGVC Aircraft
Top-1 Error Rate· 2018-05-24
7.33
best: 4.82 (EffNet-L2 (SAM))
SOTA
AutoAugment: Learning Augmentation Policies from Data arXiv:1805.09501