无需训练即可在线适应3D视觉语言模型，提升在噪声数据下的识别准确率。
Adapt-As-You-Walk Through the Clouds: Training-Free Online Test-Time Adaptation of 3D Vision-Language Foundation Models
- 通过动态原型学习构建3D缓存，实时更新类别中心以适应数据分布变化。
- 在ModelNet-40C等测试集上最高提升10.55%，显著改善模型鲁棒性。
- 适用于真实场景中数据不完整或分布偏移的3D识别任务，无需重新训练。
3D视觉语言基础模型（VLFMs）在开放世界点云处理任务中展现出强大的泛化与零样本识别能力。然而，在实际应用中，当数据存在噪声、缺失或分布与训练数据不一致时，其性能往往下降。为此，我们提出Uni-Adapter，一种基于动态原型学习的无训练在线测试时自适应（TTA）策略。通过构建3D缓存存储类特定聚类中心作为原型，并持续更新以捕捉异构数据分布中的类内变化。这些动态原型通过相似度评分实现基于缓存的逻辑值计算。同时，图结构标签平滑模块捕获原型间相似性，强化相似原型间的标签一致性。最后，采用熵加权聚合融合原始3D VLFM与优化缓存的预测结果，实现可靠适应。无需再训练，Uni-Adapter有效缓解分布偏移，在多个3D基准测试上超越现有3D VLFMs，ModelNet-40C提升10.55%，ScanObjectNN-C提升8.26%，ShapeNet-C提升4.49%。
原文摘要 · Abstract (English)
3D Vision-Language Foundation Models (VLFMs) have shown strong generalization and zero-shot recognition capabilities in open-world point cloud processing tasks. However, these models often underperform in practical scenarios where data are noisy, incomplete, or drawn from a different distribution than the training data. To address this, we propose Uni-Adapter, a novel training-free online test-time adaptation (TTA) strategy for 3D VLFMs based on dynamic prototype learning. We define a 3D cache to store class-specific cluster centers as prototypes, which are continuously updated to capture intra-class variability in heterogeneous data distributions. These dynamic prototypes serve as anchors for cache-based logit computation via similarity scoring. Simultaneously, a graph-based label smoothing module captures inter-prototype similarities to enforce label consistency among similar prototypes. Finally, we unify predictions from the original 3D VLFM and the refined 3D cache using entropy-weighted aggregation for reliable adaptation. Without retraining, Uni-Adapter effectively mitigates distribution shifts, achieving state-of-the-art performance on diverse 3D benchmarks over different 3D VLFMs, improving ModelNet-40C by 10.55%, ScanObjectNN-C by 8.26%, and ShapeNet-C by 4.49% over the source 3D VLFMs. Project page: https://mehran-tam.github.io/Uni-Adapter
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。