SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining
Researchers have developed SceneMiner, a novel pipeline for identifying challenging driving scenarios from video logs. This camera-only system utilizes a frozen vision-language backbone to generate multiple signals, including a retrieval embedding for text-based search, scene tags, and a physics-based risk score. A key innovation is "identity-preserving multi-task fine-tuning," which prevents interference between different tasks by carefully initializing and freezing parameters, allowing for efficient training of new sub-modules. AI
IMPACT Introduces a new method for identifying safety-critical driving scenarios, potentially improving autonomous vehicle training data.