AI 中文总结
针对事件云归因的点级显著性方法忽略事件时空结构的局限，提出无训练框架VGER，结合梯度与扰动证据实现事件级归因，在9种设置下均优于基线方法。
AI 中文摘要
事件相机生成稀疏且异步的事件流，为高效感知提供丰富的时空信息。基于事件的模型近期进展通过直接对异步事件建模，无需重建密集帧，展现出优异性能。然而，识别其预测背后的事件级证据，对提升模型透明度与可靠性至关重要。直接适配点云的点级显著性方法可实现细粒度归因，但忽略了事件特有的时空结构。为解决该局限，我们提出Voxel-Guided Global Event Ranking（VGER），一种适用于基于点的事件云网络的无训练归因框架。VGER结合事件级梯度证据与任务感知体素扰动证据，将区域贡献转化为事件级归因分数，同时保留细粒度分辨率。此外，VGER引入统一事件排序策略，其中高排序事件被视为预测关键事件，低排序事件则被视为对预测影响有限的事件。我们在三个基于事件的基准上，使用PointNet、PointNet++和EventMamba评估VGER。在9种数据集-骨干网络设置中，VGER在高尾和低尾删除性能上均持续优于点级显著性基线方法。
英文摘要
Event cameras produce sparse and asynchronous event streams that provide rich spatio-temporal information for efficient perception. Recent advances in event-based models have demonstrated strong performance by directly modeling asynchronous events without dense frame reconstruction. However, identifying the event-level evidence behind their predictions is crucial for improving model transparency and reliability. Directly adapting point-level saliency methods from point clouds provides fine-grained attribution but overlooks event-specific spatio-temporal structures. To address this limitation, we propose Voxel-Guided Global Event Ranking (VGER), a training-free attribution framework for point-based event cloud networks. VGER combines event-level gradient evidence with task-aware voxel perturbation evidence, transferring regional contribution into event-level attribution scores while preserving fine-grained resolution. Furthermore, VGER introduces a unified event ranking strategy, where high-ranked events are expected to be prediction-critical and low-ranked events are expected to have limited influence on predictions. We evaluate VGER on three event-based benchmarks with PointNet, PointNet++, and EventMamba. Across nine dataset-backbone settings, VGER consistently improves both high-tail and low-tail deletion performance over point-level saliency baselines.
