外观
论文arXiv 2610.2136713 天前
SATOR：通过样本自适应 Token 路由实现无反向传播的 3D 测试时自适应
原文链接：SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token Routing（arXiv 2610.21367 · 发布日期：2026-10-15）
SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token Routing
SATOR为缓解3D点云分布偏移下的性能下降，采用样本自适应Token路由做无源无反传TTA，并在三个3D损坏基准验证。
核心要点
- 3D点云TTA中，现有免反传Token清除依赖预设清除规模候选，需多次前向并增加推理成本。
- SATOR从每个样本直接导出分区阈值和路由决策，避免搜索候选清除规模。
- 其基于互补注意力与几何关系图计算Token异常分数，并用Otsu可分性划分保留与剪除Token。
- 在ModelNet40-C、ScanObjectNN-C和ShapeNet-C上，SATOR在三个3D损坏基准达到最先进准确率。
验证范围与局限：仅在ModelNet40-C、ScanObjectNN-C和ShapeNet-C三个3D损坏基准上验证。
英文摘要 (Abstract)
Test-time adaptation (TTA) mitigates the performance degradation of source-pretrained models on unlabeled test data under distribution shifts. Recent backpropagation-free token-purging methods address 3D point cloud distribution shifts by filtering unreliable tokens. However, their reliance on predefined purge-size candidates requires multiple forward passes per sample and increases inference cost. We propose SATOR (Sample-Adaptive TOken Routing), a source-free and backpropagation-free 3D TTA framework that eliminates this search by deriving both the partitioning threshold and routing decision directly from each sample. SATOR computes token abnormality scores from complementary attention and geometric relation graphs. It then derives a sample-specific partition into retained and pruned tokens via Otsu-based separability, without evaluating candidate sizes. Keep-ratio-calibrated routing then selects the pruned prediction only when its entropy, penalized by the keep ratio, is lower than that of the original prediction. Experiments on ModelNet40-C, ScanObjectNN-C, and ShapeNet-C demonstrate that SATOR achieves state-of-the-art accuracy on three 3D corruption benchmarks.
作者：Inseok Kong, Geunyoung Jung, Jiyoung Jung
来源
本页事实对应的公开页面，以原文为准。