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 |