mlsanityData to 7 Oct 2026

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

arXiv 2411.01116 ↗First posted 2 Nov 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 2 Nov 2024.

Builds on

28 of 35 references.

References · 28

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  6. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  9. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  10. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  11. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  12. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
16 more
  1. 2022Test-Time Training with Masked Autoencoderscited by 208
  2. 2022Parameter-free Online Test-time Adaptationcited by 184
  3. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  4. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  5. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  6. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  7. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  8. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
  9. 2023Continual Test-time Domain Adaptation via Dynamic Sample Selectioncited by 35
  10. 2022TTTFlow: Unsupervised Test-Time Training with Normalizing Flowcited by 33
  11. 2022MATE: Masked Autoencoders are Online 3D Test-Time Learnerscited by 23
  12. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  13. 2024Backpropagation-free Network for 3D Test-time Adaptationcited by 14
  14. 2023Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learningcited by 10
  15. 2023Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedbackcited by 10
  16. 2023Lookaround Optimizer: k steps around, 1 step averagecited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025Spectral Informed Mamba for Robust Point Cloud Processingcited by 10
  2. 2025SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Cloudscited by 4
  3. 2025Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purgingcited by 3
  4. 2025Hierarchical Adaptive networks with Task vectors for Test-Time Adaptationcited by 0
  5. 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traversescited by 0
  6. 2026MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Cloudscited by 0
  7. 2026Test Time Adaptation Methods for Point Cloud Registration in Laparoscopic Surgerycited by 0