# InCloud: Incremental Learning for Point Cloud Place Recognition

arXiv: https://arxiv.org/abs/2203.00807 · HTML: https://mlsanity.com/paper/2203.00807/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 30 of 31)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Co2L: Contrastive Continual Learning](https://mlsanity.com/paper/2106.14413/) (2021)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [Modeling the Background for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/2002.00718/) (2020)
- [PLOP: Learning without Forgetting for Continual Semantic Segmentation](https://mlsanity.com/paper/2011.11390/) (2020)
- [Adaptive Aggregation Networks for Class-Incremental Learning](https://mlsanity.com/paper/2010.05063/) (2020)
- [MinkLoc3D: Point Cloud Based Large-Scale Place Recognition](https://mlsanity.com/paper/2011.04530/) (2020)
- [Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2003.04668/) (2020)
- [Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations](https://mlsanity.com/paper/2103.06342/) (2021)
- [On Learning the Geodesic Path for Incremental Learning](https://mlsanity.com/paper/2104.08572/) (2021)
- [RECALL: Replay-based Continual Learning in Semantic Segmentation](https://mlsanity.com/paper/2108.03673/) (2021)
- [Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments](https://mlsanity.com/paper/2109.13494/) (2021)
- [PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval](https://mlsanity.com/paper/1904.09793/) (2019)
- [ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning](https://mlsanity.com/paper/2101.00407/) (2021)
- [Class Rectification Hard Mining for Imbalanced Deep Learning](https://mlsanity.com/paper/1712.03162/) (2017)
- [SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition](https://mlsanity.com/paper/2011.12430/) (2020)
- [Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning](https://mlsanity.com/paper/2012.04324/) (2020)
- [LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition](https://mlsanity.com/paper/2109.08336/) (2021)
- [Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Pooling](https://mlsanity.com/paper/2011.14497/) (2020)
- [NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation](https://mlsanity.com/paper/2103.12292/) (2021)
- [DiSCO: Differentiable Scan Context with Orientation](https://mlsanity.com/paper/2010.10949/) (2020)
- [OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios](https://mlsanity.com/paper/1903.07918/) (2019)
- [Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting](https://mlsanity.com/paper/2102.01906/) (2021)

## Built on by (most cited first, 22 of 22)

- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [Spectral Geometric Verification: Re-Ranking Point Cloud Retrieval for Metric Localization](https://mlsanity.com/paper/2210.04432/) (2022)
- [Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data](https://mlsanity.com/paper/2304.03980/) (2023)
- [CCL: Continual Contrastive Learning for LiDAR Place Recognition](https://mlsanity.com/paper/2303.13952/) (2023)
- [GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priors](https://mlsanity.com/paper/2308.04638/) (2023)
- [SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition](https://mlsanity.com/paper/2407.08260/) (2024)
- [L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space](https://mlsanity.com/paper/2307.16459/) (2023)
- [Explicit Interaction for Fusion-Based Place Recognition](https://mlsanity.com/paper/2402.17264/) (2024)
- [LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition](https://mlsanity.com/paper/2504.19186/) (2025)
- [Uncertainty-Aware Lidar Place Recognition in Novel Environments](https://mlsanity.com/paper/2210.01361/) (2022)
- [Multivariate Prototype Representation for Domain-Generalized Incremental Learning](https://mlsanity.com/paper/2309.13563/) (2023)
- [VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning](https://mlsanity.com/paper/2407.21416/) (2024)
- [Vehicle-Scene Interaction: A Text-Driven 3D Lidar Place Recognition Method for Autonomous Driving](https://mlsanity.com/paper/2503.18035/) (2025)
- [Flashbacks to Harmonize Stability and Plasticity in Continual Learning](https://mlsanity.com/paper/2506.00477/) (2025)
- [LifelongPR: Lifelong point cloud place recognition based on sample replay and prompt learning](https://mlsanity.com/paper/2507.10034/) (2025)
- [Reliable-loc: Robust sequential LiDAR global localization in large-scale street scenes based on verifiable cues](https://mlsanity.com/paper/2411.07815/) (2024)
- [Ranking-aware Continual Learning for LiDAR Place Recognition](https://mlsanity.com/paper/2505.07198/) (2025)
- [SpatiaLoc: Leveraging Multi-Level Spatial Enhanced Descriptors for Cross-Modal Localization](https://mlsanity.com/paper/2601.03579/) (2026)
- [Advanced techniques and applications of LiDAR Place Recognition in Agricultural Environments: A Comprehensive Survey](https://mlsanity.com/paper/2601.22198/) (2026)
- [Riemannian and Symplectic Geometry for Hierarchical Text-Driven Place Recognition](https://mlsanity.com/paper/2604.01598/) (2026)
- [ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation](https://mlsanity.com/paper/2504.01648/) (2025)
- [Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognition](https://mlsanity.com/paper/2511.15597/) (2025)

## Abstract (arXiv)

Place recognition is a fundamental component of robotics, and has seen tremendous improvements through the use of deep learning models in recent years. Networks can experience significant drops in performance when deployed in unseen or highly dynamic environments, and require additional training on the collected data. However naively fine-tuning on new training distributions can cause severe degradation of performance on previously visited domains, a phenomenon known as catastrophic forgetting. In this paper we address the problem of incremental learning for point cloud place recognition and introduce InCloud, a structure-aware distillation-based approach which preserves the higher-order structure of the network's embedding space. We introduce several challenging new benchmarks on four popular and large-scale LiDAR datasets (Oxford, MulRan, In-house and KITTI) showing broad improvements in point cloud place recognition performance over a variety of network architectures. To the best of our knowledge, this work is the first to effectively apply incremental learning for point cloud place recognition. Data pre-processing, training and evaluation code for this paper can be found at https://github.com/csiro-robotics/InCloud.