mlsanityData to 14 Oct 2026

PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding

arXiv 2411.00632 ↗First posted 1 Nov 2024cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's transferability towards the continually changing target domain. We introduce a multi-task setting for PCoTTA, which is practical and realistic, handling multiple tasks within one unified model during the continual adaptation. Our PCoTTA involves three key components: automatic prototype mixture (APM), Gaussian Splatted feature shifting (GSFS), and contrastive prototype repulsion (CPR). Firstly, APM is designed to automatically mix the source prototypes with the learnable prototypes with a similarity balancing factor, avoiding catastrophic forgetting. Then, GSFS dynamically shifts the testing sample toward the source domain, mitigating error accumulation in an online manner. In addition, CPR is proposed to pull the nearest learnable prototype close to the testing feature and push it away from other prototypes, making each prototype distinguishable during the adaptation. Experimental comparisons lead to a new benchmark, demonstrating PCoTTA's superiority in boosting the model's transferability towards the continually changing target domain.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 54 of its 67 references that are in the map. First posted on arXiv 1 Nov 2024.

Builds on

54 of 67 references.

References · 54

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  8. 2020PCT: Point cloud transformercited by 732
  9. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  10. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  11. 2022Continual Test-Time Domain Adaptationcited by 525
  12. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
38 more
  1. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  2. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  3. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  4. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  5. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 151
  6. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  7. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  8. 2020PointMixup: Augmentation for Point Cloudscited by 104
  9. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 104
  10. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  11. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  12. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  13. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  14. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  15. 2023ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptationcited by 58
  16. 2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
  17. 2020ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentationcited by 56
  18. 2022LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detectioncited by 55
  19. 2022A Probabilistic Framework for Lifelong Test-Time Adaptationcited by 46
  20. 2023Instance-Aware Domain Generalization for Face Anti-Spoofingcited by 42
  21. 2023Explore In-Context Learning for 3D Point Cloud Understandingcited by 40
  22. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  23. 2023Continual Test-time Domain Adaptation via Dynamic Sample Selectioncited by 35
  24. 2021Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Cloudscited by 31
  25. 2023Density-Insensitive Unsupervised Domain Adaption on 3D Object Detectioncited by 31
  26. 2022Masked Autoencoders in 3D Point Cloud Representation Learningcited by 30
  27. 2021Self-Adversarial Disentangling for Specific Domain Adaptationcited by 29
  28. 2023Exploring Sparse Visual Prompt for Domain Adaptive Dense Predictioncited by 28
  29. 2023IterativePFN: True Iterative Point Cloud Filteringcited by 28
  30. 2021Domain Adaptation on Point Clouds via Geometry-Aware Implicitscited by 26
  31. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  32. 2024DGMamba: Domain Generalization via Generalized State Space Modelcited by 21
  33. 2023Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentationcited by 20
  34. 2024Test-Time Domain Generalization for Face Anti-Spoofingcited by 20
  35. 2023Effective Restoration of Source Knowledge in Continual Test Time Adaptationcited by 15
  36. 2023LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptationcited by 14
  37. 2024DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understandingcited by 13
  38. 2023Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learningcited by 10

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 4.

11 papers.

  1. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  2. 2025Test-Time Distillation for Continual Model Adaptationcited by 5
  3. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  4. 2025APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Cloudscited by 2
  5. 2025CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Drivingcited by 1
  6. 2025CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teachercited by 1
  7. 2026Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directionscited by 1
  8. 2025Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuningcited by 0
  9. 2026Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understandingcited by 0
  10. 2026Deformation-based In-Context Learning for Point Cloud Understandingcited by 0
  11. 2026Test Time Adaptation Methods for Point Cloud Registration in Laparoscopic Surgerycited by 0