TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation

Résumé : Automatic augmentation methods have recently become a crucial pillar for strong model performance in vision tasks. Current methods are mostly a trade-off between being simple, in-expensive or well-performing. We present a most simple automatic augmentation baseline, TrivialAugment, that outperforms previous methods almost for free. It is parameter-free and only applies a single augmentation to each image. To us, TrivialAugment's effectiveness is very unexpected. Thus, we performed very thorough experiments on its performance. First, we compare TrivialAugment to previous state-of-the-art methods in a plethora of scenarios. Then, we perform multiple ablation studies with different augmentation spaces, augmentation methods and setups to understand the crucial requirements for its performance. We condensate our learnings into recommendations to automatic augmentation users. Additionally, we provide a simple interface to use multiple automatic augmentation methods in any codebase, 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.