让多任务模型自动应对天气变化，提升自动驾驶可靠性。
RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions
- 根据输入图像的模糊程度，动态选择适合的低秩适配模块。
- 在PASCAL数据集上混合天气下性能比基线高44.4%。
- 适合需要抗干扰能力的自动驾驶视觉系统研究者。
鲁棒的多任务学习对真实环境中的自主系统至关重要，恶劣天气会严重降低模型性能与可靠性。本文提出RobuMTL，一种新架构，通过混合专家机制，根据输入扰动动态选择特定任务的分层低秩适配（LoRA）模块和LoRA专家组，实现基于输入特征的自适应专业化。该框架在PASCAL和NYUD-v2数据集上评估，对比单任务模型、标准多任务学习基线及前沿方法。在PASCAL上，单一扰动下平均相对提升2.8%，混合天气下最高提升44.4%；在NYUD-v2上，各任务平均相对提升9.7%。代码已开源。
原文摘要 · Abstract (English)
Robust Multi-Task Learning (MTL) is crucial for autonomous systems operating in real-world environments, where adverse weather conditions can severely degrade model performance and reliability. In this paper, we introduce RobuMTL, a novel architecture designed to adaptively address visual degradation by dynamically selecting task-specific hierarchical Low-Rank Adaptation (LoRA) modules and a LoRA expert squad based on input perturbations in a mixture-of-experts fashion. Our framework enables adaptive specialization based on input characteristics, improving robustness across diverse real-world conditions. To validate our approach, we evaluated it on the PASCAL and NYUD-v2 datasets and compared it against single-task models, standard MTL baselines, and state-of-the-art methods. On the PASCAL benchmark, RobuMTL delivers a +2.8% average relative improvement under single perturbations and up to +44.4% under mixed weather conditions compared to the MTL baseline. On NYUD-v2, RobuMTL achieves a +9.7% average relative improvement across tasks. The code is available at GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。