Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation

TL;DR

This paper introduces two novel automated data augmentation methods, SmartAugment and SmartSamplingAugment, specifically designed for semantic segmentation, achieving state-of-the-art results and competitive performance with less resource consumption.

Contribution

It is the first to focus on automated data augmentation for semantic segmentation, proposing two new methods that improve performance and efficiency.

Findings

SmartAugment achieves state-of-the-art performance.

SmartSamplingAugment competes with resource-intensive methods.

Ablation studies validate the design choices.

Abstract

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.