Table 1 Different type of pixel and spatial level image transformations used in this study.
From: Melanoma segmentation using deep learning with test-time augmentations and conditional random fields
Augmentation type | Augmentation |
|---|---|
Pixel level | Motion blur |
Random brightness | |
Random contrast | |
Random gamma | |
Hue saturation value | |
RGB shift | |
Grayscale | |
Spatial level | Random 90 rotation |
Vertical flip | |
Horizontal flip |
