Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approach
This addresses the challenge of expensive and impractical data collection for adverse conditions in autonomous driving and similar domains, offering a domain adaptation solution.
The paper tackles the problem of semantic segmentation models struggling with adverse weather and nighttime conditions by proposing a novel architecture that uses synthetic data with weather and time-of-day supervisors, improving mIoU by 14 percentage points on the ACDC dataset while maintaining 75% mIoU on Cityscapes.
Recent semantic segmentation models perform well under standard weather conditions and sufficient illumination but struggle with adverse weather conditions and nighttime. Collecting and annotating training data under these conditions is expensive, time-consuming, error-prone, and not always practical. Usually, synthetic data is used as a feasible data source to increase the amount of training data. However, just directly using synthetic data may actually harm the model's performance under normal weather conditions while getting only small gains in adverse situations. Therefore, we present a novel architecture specifically designed for using synthetic training data for domain adaptation. We propose a simple yet powerful addition to DeepLabV3+ by using weather and time-of-the-day supervisors trained with multi-task learning, making it both weather and nighttime aware, which improves its mIoU accuracy by $14$ percentage points on the ACDC dataset while maintaining a score of $75\%$ mIoU on the Cityscapes dataset. Our code is available at https://github.com/lsmcolab/Semantic-Segmentation-under-Adverse-Conditions.