DiffPrompter：用于恶劣条件下语义分割的可微隐式视觉提示
DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions
AI总结：
提出可微视觉与潜在提示机制 DiffPrompter，结合 $\ abla$HFC 图像处理模块与联合训练策略，显著提升恶劣天气下基础模型语义分割及分布外场景性能。
摘要：
恶劣天气场景下的语义分割是自动驾驶系统的关键任务。尽管基础模型已展现出潜力，但为应对更具挑战性的场景，对专用适配器的需求变得显而易见。我们引入了 DiffPrompter，这是一种新颖的可微视觉与潜在提示机制，旨在扩展基础模型中现有适配器的学习能力。我们提出的 $\ abla$HFC 图像处理模块在恶劣天气条件下表现尤为出色，而传统方法往往在这些条件下表现不佳。此外，我们研究了联合训练视觉与潜在提示的优势，证明这种组合方法能显著提升在分布外场景下的性能。我们的可微视觉提示利用并行与串联架构生成提示，有效改善了恶劣条件下的目标分割任务。通过一系列全面的实验与评估，我们提供了支持该方法有效性的实证证据。项目页面见 https://diffprompter.github.io。
英文摘要：
Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging scenarios. We introduce DiffPrompter, a novel differentiable visual and latent prompting mechanism aimed at expanding the learning capabilities of existing adaptors in foundation models. Our proposed $\nabla$HFC image processing block excels particularly in adverse weather conditions, where conventional methods often fall short. Furthermore, we investigate the advantages of jointly training visual and latent prompts, demonstrating that this combined approach significantly enhances performance in out-of-distribution scenarios. Our differentiable visual prompts leverage parallel and series architectures to generate prompts, effectively improving object segmentation tasks in adverse conditions. Through a comprehensive series of experiments and evaluations, we provide empirical evidence to support the efficacy of our approach. Project page at https://diffprompter.github.io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
