用时空轨迹建模物体层级，光锥几何让视觉系统更懂部分与整体关系。
Light Cones For Vision: Simple Causal Priors For Visual Hierarchy
- 将物体视为时空中的连续轨迹，不同层级共享空间位置但时间坐标不同。
- 洛伦兹几何下准确率达0.479-0.661，比欧氏几何提升6倍，显著超越随机水平。
- 适合研究视觉层次结构、因果建模或轻量级模型设计的学者参考。
标准视觉模型将物体视为欧几里得空间中的独立点，无法捕捉如部分-整体这样的层级结构。本文提出世界线槽注意力（Worldline Slot Attention），将物体建模为时空中的持久轨迹——每个物体在不同层级具有多个槽，共享空间位置但时间坐标不同。该架构在缺乏几何结构时表现失败：欧氏世界线准确率仅0.078，低于随机猜测的0.33；而洛伦兹世界线在三个数据集上达到0.479–0.661的准确率，实现6倍提升，并在20多次独立实验中复现。洛伦兹几何优于双曲嵌入，表明视觉层级结构依赖因果性（时间依赖）而非树状分支。结果证明，发现层级结构需编码非对称因果性的几何先验，这在欧氏空间中缺失，但在洛伦兹光锥中天然存在，且仅需11K参数即可实现。代码已开源：https://github.com/iclrsubmissiongram/loco。
原文摘要 · Abstract (English)
Standard vision models treat objects as independent points in Euclidean space, unable to capture hierarchical structure like parts within wholes. We introduce Worldline Slot Attention, which models objects as persistent trajectories through spacetime worldlines, where each object has multiple slots at different hierarchy levels sharing the same spatial position but differing in temporal coordinates. This architecture consistently fails without geometric structure: Euclidean worldlines achieve 0.078 level accuracy, below random chance (0.33), while Lorentzian worldlines achieve 0.479-0.661 across three datasets: a 6x improvement replicated over 20+ independent runs. Lorentzian geometry also outperforms hyperbolic embeddings showing visual hierarchies require causal structure (temporal dependency) rather than tree structure (radial branching). Our results demonstrate that hierarchical object discovery requires geometric structure encoding asymmetric causality, an inductive bias absent from Euclidean space but natural to Lorentzian light cones, achieved with only 11K parameters. The code is available at: https://github.com/iclrsubmissiongram/loco.
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。