用单次推理提取多种场景信号，实现无标签高危驾驶场景挖掘。
SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining
- 基于冻结视觉语言模型，一次前向传播生成检索嵌入、多标签场景分布和风险评分。
- 多任务训练中新增模块导致共享特征退化，引入身份保持策略解决此问题。
- 仅微调约10万参数，即可在20个场景标签上达到mAP 0.4614，适合自动驾驶安全分析。
从驾驶日志中挖掘高难度、关乎安全的场景，受限于缺乏难度标签，单一代理（如碰撞风险、轨迹模糊或语义罕见性）均无法独立有效识别此类场景。本文提出SceneMiner，一个仅依赖摄像头的统一鸟瞰视图流水线，在单次前向传播中，通过冻结的视觉语言主干生成互补的挖掘信号：支持文本提示的场景检索嵌入、多标签场景标记分布与连续物理风险评分（运动预测为副产品，非贡献）。构建多头模型揭示核心发现——跨任务干扰：新增或升级某头部会改变共享激活流，导致权重冻结的兄弟头部性能下降，单纯冻结参数不足以避免此问题。本文提出的身份保持多任务微调方法，通过零初始化每个新子模块，并冻结所有输入共享流的参数，确保各挖掘头部在训练过程中比特级保持不变，仅需微调约10.2万参数。标签头部在20个场景标签上实现mAP 0.4614（micro-F1 0.5557），通过将每场景划分为32个视觉标记进行池化；嵌入头部支持文本提示检索，定性验证有效。代码已公开。
原文摘要 · Abstract (English)
Mining hard, safety-critical scenes from driving logs is bottlenecked by the absence of difficulty labels, and no single proxy, collision risk, trajectory ambiguity, or semantic rarity suffices to find such scenes on its own. We present SceneMiner, a unified, camera-only bird's-eye-view pipeline that emits complementary mining signals from a frozen vision-language backbone in a single forward pass, with no LiDAR or radar: a retrieval embedding for text-prompted scenario search, a multi-label scene-tag distribution, and a continuous physics-based risk score (a motion forecast is a byproduct, not a contribution). Building such a multi-head model exposes our central finding, a failure mode we term cross-task interference: adding or upgrading one head shifts a shared activation stream and degrades weight-frozen sibling heads, so freezing parameters alone is insufficient. Our contribution, identity-preserving multi-task fine-tuning, removes this interference by zero-initializing every new sub-module and freezing every parameter that feeds the shared stream. The mining heads are thereby preserved bit-identically while training only ~102k parameters. The tagging head reaches mAP 0.4614 (micro-F1 0.5557) on 20 scene tags by pooling each scene into 32 visual tokens, and the embedding head supports text-prompted retrieval, validated qualitatively. Code is available at: https://anonymous.4open.science/r/sceneminer_anonymous-64E5
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。