Ultra：面向恶劣天气下可靠的修复-分割协作的无监督跨任务优化
Ultra: Unsupervised Cross-Task Optimization for Reliable Restoration Segmentation Collaboration under Adverse Weather
浏览论文内容
中文总结 AI 辅助
本研究针对恶劣天气下修复-分割协作的无监督跨任务优化问题，提出Ultra框架，含CTDN与CMIL模块，在UDA-ASS基准上实现最优分割性能，还可泛化至修复与检测协作任务。
中文摘要 AI 辅助
恶劣天气语义分割的无监督域适应（UDA-ASS）旨在将带标注的正常天气图像的语义知识迁移至无标注的恶劣环境。现有方法默认假设修复与分割能提供相互有益的指导，但在严重退化且无目标域监督的情况下，跨任务优化方向的有效性根本无法确定，会导致幻觉驱动的误差传播。本研究提出一种新型无监督修复-分割协作学习框架Ultra，将跨任务交互重构为不确定性下的方向选择与因果效应估计，通过候选方向生成与基于干预的过滤实现可靠协作。具体而言，提出CTDN与CMIL：前者利用互补的视觉结构与语义信息生成候选优化方向，并执行修复与分割间的协作方向选择；后者将跨任务信息传递从基于相关性的传播重构为因果效应评估，抑制幻觉传播。在三个广泛使用的UDA-ASS基准上开展的大量实验表明，该框架取得了最优的分割性能；除分割任务外，其在无监督修复任务上的表现优于现有UDA-ASS修复方法，且可泛化至无监督修复与目标检测的协作任务。代码与模型将发布于该https URL。
英文摘要
Unsupervised Domain Adaptation for Adverse Weather Semantic Segmentation (UDA-ASS) aims to transfer semantic knowledge from labeled normal-weather images to unlabeled adverse environments. Existing approaches implicitly assume that restoration and segmentation provide mutually beneficial guidance. However, under severe degradation and without target-domain supervision, the validity of cross-task optimization directions becomes fundamentally unidentifiable, leading to hallucination-driven error propagation. In this work, we propose a novel Unsupervised Restoration-Segmentation Collaborative Learning Framework (Ultra), which reframes cross-task interaction as direction selection under uncertainty and causal effect estimation, enabling reliable collaboration through candidate direction generation and intervention-based filtering. In detail, we propose CTDN and CMIL. The former exploits complementary visual structures and semantic information to generate candidate optimization directions and performs cooperative direction selection between restoration and segmentation. The latter reformulates cross-task information transfer from correlation-based propagation into causal effect assessment, suppressing hallucination propagation. Extensive experiments on three widely used UDA-ASS benchmarks demonstrate state-of-the-art segmentation performance. Beyond segmentation, our framework achieves better unsupervised restoration results than existing UDA-ASS restoration methods and generalizes to unsupervised restoration and object detection collaboration tasks. Code and models will be available at https://github.com/Wang-Shiqin/Ultra.
发表机构
- Wuhan University（武汉大学）
- Beijing Institute of Technology（北京理工大学）
- Zhongguancun Academy（中关村学院）
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
