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

TL;DR

This paper introduces a semi-supervised semantic segmentation pipeline for adverse weather conditions, leveraging UniMatch V2 and test-time augmentation, with code available on GitHub.

Contribution

The novel approach fully exploits the WeatherProof dataset using semi-supervised training with UniMatch V2 and applies test-time augmentation for robustness.

Findings

Achieved improved segmentation accuracy under adverse weather conditions.

Utilized semi-supervised learning to maximize data utility without external data.

Enhanced robustness through test-time augmentation.

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.