Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging
This work addresses distribution shifts in real-world 3D point cloud classification, offering an incremental improvement over existing methods.
The paper tackles test-time adaptation for 3D point cloud classification by combining sampling variation with weight averaging, resulting in consistent performance improvements across multiple datasets and backbones while maintaining minimal resource overhead.
Test-Time Adaptation (TTA) addresses distribution shifts during testing by adapting a pretrained model without access to source data. In this work, we propose a novel TTA approach for 3D point cloud classification, combining sampling variation with weight averaging. Our method leverages Farthest Point Sampling (FPS) and K-Nearest Neighbors (KNN) to create multiple point cloud representations, adapting the model for each variation using the TENT algorithm. The final model parameters are obtained by averaging the adapted weights, leading to improved robustness against distribution shifts. Extensive experiments on ModelNet40-C, ShapeNet-C, and ScanObjectNN-C datasets, with different backbones (Point-MAE, PointNet, DGCNN), demonstrate that our approach consistently outperforms existing methods while maintaining minimal resource overhead. The proposed method effectively enhances model generalization and stability in challenging real-world conditions.