Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915083173494784 |
|---|---|
| author | Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Dastani, Sahar Cheraghalikhani, Milad Osowiech, David Beizaee, Farzad vargas-hakim, Gustavo adolfo. Ayed, Ismail Ben Desrosiers, Christian |
| author_facet | Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Dastani, Sahar Cheraghalikhani, Milad Osowiech, David Beizaee, Farzad vargas-hakim, Gustavo adolfo. Ayed, Ismail Ben Desrosiers, Christian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01116 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging Bahri, Ali Yazdanpanah, Moslem Noori, Mehrdad Dastani, Sahar Cheraghalikhani, Milad Osowiech, David Beizaee, Farzad vargas-hakim, Gustavo adolfo. Ayed, Ismail Ben Desrosiers, Christian Computer Vision and Pattern Recognition 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. |
| title | Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.01116 |