A Robust Semantic Segmentation Pipeline for the CVPR 2026 8th UG2+ Challenge Track 2
This is an incremental solution for the specific challenge of semantic segmentation in adverse weather, targeting the CVPR 2026 UG2+ Challenge.
The authors propose a semi-supervised segmentation pipeline for adverse weather conditions, using UniMatch V2 as baseline and treating degraded-weather images as unlabeled data, achieving robust performance on the WeatherProof dataset without external data.
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.