Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation
This addresses the problem of efficient and effective data augmentation for semantic segmentation, providing the first study in this domain, though it is incremental relative to prior work in image classification and object detection.
The paper tackles automated data augmentation for semantic image segmentation, introducing SmartAugment and SmartSamplingAugment, with SmartAugment achieving new state-of-the-art performance and SmartSamplingAugment competing with resource-intensive methods while outperforming cheap ones.
Data augmentation methods enrich datasets with augmented data to improve the performance of neural networks. Recently, automated data augmentation methods have emerged, which automatically design augmentation strategies. Existing work focuses on image classification and object detection, whereas we provide the first study on semantic image segmentation and introduce two new approaches: \textit{SmartAugment} and \textit{SmartSamplingAugment}. SmartAugment uses Bayesian Optimization to search over a rich space of augmentation strategies and achieves a new state-of-the-art performance in all semantic segmentation tasks we consider. SmartSamplingAugment, a simple parameter-free approach with a fixed augmentation strategy competes in performance with the existing resource-intensive approaches and outperforms cheap state-of-the-art data augmentation methods. Further, we analyze the impact, interaction, and importance of data augmentation hyperparameters and perform ablation studies, which confirm our design choices behind SmartAugment and SmartSamplingAugment. Lastly, we will provide our source code for reproducibility and to facilitate further research.