针对车道检测在分布变化下的遗忘问题，提出动态路由的高效适配方法。
Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift
- 为不同数据分布创建独立分支，仅微调部分组件，保留原始模型
- 在多个分布上实现接近最优的F1分数，参数量远低于独立建模
- 通过对比学习动态识别输入分布，自动选择对应分支推理
车道检测模型通常在封闭世界设定下评估，即训练与测试使用相同数据集。我们观察到，即使在同一领域内，跨数据集的分布偏移也会导致微调时严重灾难性遗忘。为此，我们首先在源分布上训练基础模型，再通过创建独立分支，仅微调选定组件并保持原始源分支固定，以适应每个新的目标分布。基于组件级分析，我们确定了有效的微调策略，实现参数高效适配。推理时，我们采用监督对比学习模型识别输入分布，并动态路由至对应分支。该框架在多个分布上达到近最优的F1分数，同时显著减少参数量，优于为每种分布单独训练模型的方法。
原文摘要 · Abstract (English)
Lane detection models are often evaluated in a closed-world setting, where training and testing occur on the same dataset. We observe that, even within the same domain, cross-dataset distribution shifts can cause severe catastrophic forgetting during fine-tuning. To address this, we first train a base model on a source distribution and then adapt it to each new target distribution by creating separate branches, fine-tuning only selected components while keeping the original source branch fixed. Based on a component-wise analysis, we identify effective fine-tuning strategies for target distributions that enable parameter-efficient adaptation. At inference time, we propose using a supervised contrastive learning model to identify the input distribution and dynamically route it to the corresponding branch. Our framework achieves near-optimal F1-scores while using significantly fewer parameters than training separate models for each distribution.
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。