YOLOO: You Only Learn from Others Once

원문 초록

Multi-modal 3D multi-object tracking (MOT) typically necessitates extensive computational costs of deep neural networks (DNNs) to extract multi-modal representations. In this paper, we propose an intriguing question: May we learn from multiple modalities only during training to avoid multi-modal input in the inference phase? To answer it, we propose \textbf{YOLOO}, a novel multi-modal 3D MOT paradigm: You Only Learn from Others Once. YOLOO empowers the point cloud encoder to learn a unified tri-modal representation (UTR) from point clouds and other modalities, such as images and textual cues, all at once. Leveraging this UTR, YOLOO achieves efficient tracking solely using the point cloud encoder without compromising its performance, fundamentally obviating the need for computationally intensive DNNs. Specifically, YOLOO includes two core components: a unified tri-modal encoder (UTEnc) and a flexible geometric constraint (F-GC) module. UTEnc integrates a point cloud encoder with image and text encoders adapted from pre-trained CLIP. It seamlessly fuses point cloud information with rich visual-textual knowledge from CLIP into the point cloud encoder, yielding highly discriminative UTRs that facilitate the association between trajectories and detections. Additionally, F-GC filters out mismatched associations with similar representations but significant positional discrepancies. It further enhances the robustness of UTRs without requiring any scene-specific tuning, addressing a key limitation of customized geometric constraints (e.g., 3D IoU). Lastly, high-quality 3D trajectories are generated by a traditional data association component. By integrating these advancements into a multi-modal 3D MOT scheme, our YOLOO achieves substantial gains in both robustness and efficiency.