2024/06/09 by Jun Yu, Yu, Jun, Yunxiang Zhang +7
Computer Science · Social Sciences · #Advanced Computational Techniques and Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Geographic Information Systems Studies
paper · pdf · doi:10.48550/arxiv.2406.05837
openalex publication_date 2024/06/09 · openalex created_date 2024/06/12 · openalex updated_date 2026/07/28
In this report, we present our solution for the semantic segmentation in adverse weather, in UG2+ Challenge at CVPR 2024. To achieve robust and accurate segmentation results across various weather conditions, we initialize the InternImage-H backbone with pre-trained weights from the large-scale joint dataset and enhance it with the state-of-the-art Upernet segmentation method. Specifically, we utilize offline and online data augmentation approaches to extend the train set, which helps us to further improve the performance of the segmenter. As a result, our proposed solution demonstrates advanced performance on the test set and achieves 3rd position in this challenge.