홈 › Papers

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

2024-11-02 · Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori, Sahar Dastani, Milad Cheraghalikhani, David Osowiech, Farzad Beizaee, Gustavo adolfo. vargas-hakim, Ismail Ben Ayed, Christian Desrosiers

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.

📄 PDF Abstract BibTeX arXiv:2411.01116

Code (1)

AliBahri94/SVWA_TTA 공식 구현 pytorch

Tasks

3D Point Cloud Classification Point Cloud Classification Test-time Adaptation

CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation

2024-07-23 · Hajin Shim, Changhun Kim, Eunho Yang

3D point clouds captured from real-world sensors frequently encompass noisy points due to various obstacles, such as occlusion, limited resolution, and variations in scale. These challenges hinder the deployment of pre-t…

Computational Efficiency Test-time Adaptation

SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds

2025-05-26 · Ali Bahri, Moslem Yazdanpanah, Sahar Dastani, Mehrdad Noori 외

Test-Time Training (TTT) has emerged as a promising solution to address distribution shifts in 3D point cloud classification. However, existing methods often rely on computationally expensive backpropagation during adapt…

3D Point Cloud Classification Computational Efficiency Point Cloud Classification

Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models

2024-11-21 · Hamidreza Dastmalchi, Aijun An, Ali Cheraghian, Shafin Rahman 외

Test-time adaptation (TTA) of 3D point clouds is crucial for mitigating discrepancies between training and testing samples in real-world scenarios, particularly when handling corrupted point clouds. LiDAR data, for insta…

Denoising Self-Supervised Learning Test-time Adaptation

Leveraging Temporal Information for 3D Detection and Domain Adaptation

2020-06-30 · Cunjun Yu, Zhongang Cai, Daxuan Ren, Haiyu Zhao

Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focuses on detecting objects in a single 360-…

Autonomous Driving Domain Adaptation

3D Test-time Adaptation via Graph Spectral Driven Point Shift

2025-07-24 · Xin Wei, Qin Yang, Yijie Fang, Mingrui Zhu 외 arxiv

While test-time adaptation (TTA) methods effectively address domain shifts by dynamically adapting pre-trained models to target domain data during online inference, their application to 3D point clouds is hindered by the…

3D Point Cloud Classification Test-time Adaptation Point Clouds