A Robust Semantic Segmentation Pipeline for the CVPR 2026 8th UG2+ Challenge Track 2

2026-05-21

AI Summary

This work addresses the performance degradation of semantic segmentation under adverse weather conditions by proposing a semi-supervised learning approach that relies solely on the WeatherProof dataset. Treating all degraded weather images as unlabeled data, the method leverages the UniMatch V2 framework combined with test-time augmentation (TTA) to fully exploit the intrinsic data distribution of the challenge without incorporating any external data. This strategy significantly enhances model robustness and segmentation accuracy under complex weather conditions such as rain and fog, achieving outstanding performance in CVPR 2026 UG2+ Challenge Track 2.

Abstract

This report presents our solution for the WeatherProof Dataset Challenge, namely CVPR 2026 8th UG2+ Challenge Track 2: Semantic Segmentation in Adverse Weather. For the semantic segmentation task under adverse weather conditions, we propose a semi-supervised segmentation pipeline. Our method is trained exclusively on the WeatherProof dataset, without using any additional external data. Specifically, we adopt UniMatch V2 as the baseline model and treat all degraded-weather images as unlabeled data for semi-supervised training, thereby fully exploiting the data distribution provided by the challenge. During inference, we further apply test-time augmentation to improve the robustness and segmentation accuracy of the final predictions. The code is publicly available at: https://github.com/ylb888/weatherproof-challenge-unimatchv2.

Problem

• semantic segmentation
• adverse weather
• robustness
• WeatherProof Dataset
• CVPR UG2+ Challenge

Innovation

• semi-supervised segmentation
• adverse weather
• UniMatch V2
• test-time augmentation
• WeatherProof dataset