TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation
This work addresses the need for simple and cost-effective data augmentation in computer vision, though it appears incremental as it builds on existing automatic augmentation research.
The paper tackles the problem of automatic data augmentation in vision tasks by introducing TrivialAugment, a parameter-free method that applies a single augmentation per image, and shows it outperforms previous state-of-the-art methods in various image classification scenarios.
Automatic augmentation methods have recently become a crucial pillar for strong model performance in vision tasks. While existing automatic augmentation methods need to trade off simplicity, cost and performance, we present a most simple baseline, TrivialAugment, that outperforms previous methods for almost free. TrivialAugment is parameter-free and only applies a single augmentation to each image. Thus, TrivialAugment's effectiveness is very unexpected to us and we performed very thorough experiments to study its performance. First, we compare TrivialAugment to previous state-of-the-art methods in a variety of image classification scenarios. Then, we perform multiple ablation studies with different augmentation spaces, augmentation methods and setups to understand the crucial requirements for its performance. Additionally, we provide a simple interface to facilitate the widespread adoption of automatic augmentation methods, as well as our full code base for reproducibility. Since our work reveals a stagnation in many parts of automatic augmentation research, we end with a short proposal of best practices for sustained future progress in automatic augmentation methods.