mlsanityData to 14 Oct 2026

Ranking-aware Continual Learning for LiDAR Place Recognition

arXiv 2505.07198 ↗First posted 12 May 2025cs.CVcited by 1

On the map: Knowledge distillation → Detection and dense prediction distillation

Abstract (arXiv)

Place recognition plays a significant role in SLAM, robot navigation, and autonomous driving applications. Benefiting from deep learning, the performance of LiDAR place recognition (LPR) has been greatly improved. However, many existing learning-based LPR methods suffer from catastrophic forgetting, which severely harms the performance of LPR on previously trained places after training on a new environment. In this paper, we introduce a continual learning framework for LPR via Knowledge Distillation and Fusion (KDF) to alleviate forgetting. Inspired by the ranking process of place recognition retrieval, we present a ranking-aware knowledge distillation loss that encourages the network to preserve the high-level place recognition knowledge. We also introduce a knowledge fusion module to integrate the knowledge of old and new models for LiDAR place recognition. Our extensive experiments demonstrate that KDF can be applied to different networks to overcome catastrophic forgetting, surpassing the state-of-the-art methods in terms of mean Recall@1 and forgetting score.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. Builds on 37 of its 51 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

37 of 51 references.

References · 37

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2016Learning without Forgettingcited by 2,496
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  5. 2020Knowledge Distillation: A Surveycited by 1,603
  6. 2017Continual Learning with Deep Generative Replaycited by 1,158
  7. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  8. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  9. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  10. 2019Relational Knowledge Distillationcited by 889
  11. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  12. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 681
25 more
  1. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  2. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 198
  3. 2020MinkLoc3D: Point Cloud Based Large-Scale Place Recognitioncited by 115
  4. 2020Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrievalcited by 98
  5. 2019Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challengescited by 93
  6. 2021Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworkscited by 56
  7. 2021LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognitioncited by 51
  8. 2022Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Trainingcited by 45
  9. 2020Semantic Graph Based Place Recognition for 3D Point Cloudscited by 43
  10. 2020Unsupervised Model Adaptation for Continual Semantic Segmentationcited by 42
  11. 2023A Survey on Global LiDAR Localization: Challenges, Advances and Open Problemscited by 40
  12. 2020Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Poolingcited by 38
  13. 2020Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detectioncited by 37
  14. 2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
  15. 2021TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fieldscited by 29
  16. 2022Lifelong Person Re-Identification via Knowledge Refreshing and Consolidationcited by 26
  17. 2024General Place Recognition Survey: Towards Real-World Autonomycited by 23
  18. 2022InCloud: Incremental Learning for Point Cloud Place Recognitioncited by 22
  19. 2023LiDAR-Based Place Recognition For Autonomous Driving: A Surveycited by 21
  20. 2021Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detectioncited by 16
  21. 2022Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representationcited by 16
  22. 2022BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognitioncited by 13
  23. 2021AirLoop: Lifelong Loop Closure Detectioncited by 11
  24. 2022SphereVLAD++: Attention-based and Signal-enhanced Viewpoint Invariant Descriptorcited by 8
  25. 2023CCL: Continual Contrastive Learning for LiDAR Place Recognitioncited by 8

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognitioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
  2. 2024TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation
  3. 2024OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition
  4. 2021On Learning the Geodesic Path for Incremental Learning
  5. 2026EdgeLPR: On the Deep Neural Network trade-off between Precision and Performance in LiDAR Place Recognition
  6. 2025Diffusion Based Robust LiDAR Place Recognition
  7. 2026Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding
  8. 2026TASSO: TAsk-Specific Subspace Optimization for Continual Learning of Vision-Language Models