Blake Gella1*, Howard Zhang1*, Rishi Upadhyay1, Tiffany Chang1, Nathan Wei1, Matthew Waliman1, Yunhao Ba1, Celso de Melo3, Alex Wong2, Achuta Kadambi1 University of California, Los Angeles1, Yale University2, US Army Research Laboratory3
https://visual.ee.ucla.edu/weatherproof_clip.htm/
We propose a method to infer semantic segmentation maps from images captured under adverse weather conditions. We begin by examining existing models on images degraded by weather conditions such as rain, fog, or snow, and found that they exhibit a large performance drop as compared to those captured under clear weather. To control for changes in scene structures, we propose WeatherProof, the first semantic segmentation dataset with accurate clear and adverse weather image pairs that share an underlying scene. Through this dataset, we analyze the error modes in existing models and found that they were sensitive to the highly complex combination of different weather effects induced on the image during capture. To improve robustness, we propose a way to use language as guidance by identifying contributions of adverse weather conditions and injecting that as “side information”. Models trained using our language guidance exhibit performance gains by up to 10.2% in mIoU on WeatherProof, up to 8.44% in mIoU on the widely used ACDC dataset compared to standard training techniques, and up to 6.21% in mIoU on the ACDC dataset as compared to previous SOTA methods.
@article{gella2023weatherproof,
title={WeatherProof: A Paired-Dataset Approach to Semantic Segmentation in Adverse Weather},
author={Gella, Blake and Zhang, Howard and Upadhyay, Rishi and Chang, Tiffany and Waliman, Matthew and Ba, Yunhao and Wong, Alex and Kadambi, Achuta},
journal={arXiv preprint arXiv:2312.09534},
year={2023}
}
The dataset can be found here.
Please only use the code and dataset for research purposes.
Howard Zhang
UCLA, Electrical and Computer Engineering Department
hwdz15508@g.ucla.edu