RangeAugment: Efficient Online Augmentation with Range Learning
Machine Learning Research at Apple
JANUARY 3, 2023
State-of-the-art automatic augmentation methods (e.g., AutoAugment and RandAugment) for visual recognition tasks diversify training data using a large set of augmentation operations. The range of magnitudes of many augmentation operations (e.g., brightness and contrast) is continuous. Therefore, to make search computationally tractable, these methods use fixed and manually-defined magnitude ranges for each operation, which may lead to sub-optimal policies.
130 130
Let's personalize your content