# Solution for CVPR 2024 UG2+ Challenge Track on All Weather Semantic Segmentation

Source: [Solution for CVPR 2024 UG2+ Challenge Track on All Weather Semantic Segmentation](<https://www.sota2.com/research/paper/68fa73881e209131cea5d03d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:51:14.866Z

Authors: Jun Yu, Yunxiang Zhang, Fengzhao Sun, Leilei Wang, Renjie Lu

Published: 2024-06-09T15:56:35.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2406.05837>)

[PDF](<https://arxiv.org/pdf/2406.05837.pdf>)