Skip to content

Benchmarks and a comparison with baseline augmentation strategies

Here is a comparison between a baseline augmentation strategy and an augmentation policy discovered by AutoAlbument for different classification and semantic segmentation tasks. You can read more about these benchmarks in the autoalbument-benchmarks repository.

Classification

Dataset Baseline Top-1 Accuracy AutoAlbument Top-1 Accuracy
CIFAR10 91.79 96.02
SVHN 98.31 98.48
ImageNet 73.27 75.17

Semantic segmentation

Dataset Baseline mIOU AutoAlbument mIOU
Pascal VOC 73.34 75.55
Cityscapes 79.47 79.92