Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging

TL;DR

This paper introduces a test-time adaptation method for 3D point cloud classification that uses sampling variation and weight averaging to improve robustness against distribution shifts, demonstrating superior performance across multiple datasets and models.

Contribution

The paper presents a novel TTA approach combining sampling variation with weight averaging for 3D point cloud classification, enhancing robustness without significant resource overhead.

Findings

Consistently outperforms existing TTA methods on multiple datasets.

Improves model robustness against distribution shifts in real-world scenarios.

Maintains minimal resource overhead during adaptation.

Abstract

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.