# InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation

arXiv: https://arxiv.org/abs/2302.09886 · HTML: https://mlsanity.com/paper/2302.09886/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 62 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 30 of 32)

- [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)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [SO-Net: Self-Organizing Network for Point Cloud Analysis](https://mlsanity.com/paper/1803.04249/) (2018)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning](https://mlsanity.com/paper/1904.03137/) (2019)
- [Federated Class-Incremental Learning](https://mlsanity.com/paper/2203.11473/) (2022)
- [Distilling Causal Effect of Data in Class-Incremental Learning](https://mlsanity.com/paper/2103.01737/) (2021)
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://mlsanity.com/paper/1911.02744/) (2019)
- [On Learning the Geodesic Path for Incremental Learning](https://mlsanity.com/paper/2104.08572/) (2021)
- [Federated Mutual Learning](https://mlsanity.com/paper/2006.16765/) (2020)
- [What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation](https://mlsanity.com/paper/2004.11500/) (2020)
- [Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN](https://mlsanity.com/paper/1811.07782/) (2018)
- [Self-Training for Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2012.03362/) (2020)
- [DeeSIL: Deep-Shallow Incremental Learning](https://mlsanity.com/paper/1808.06396/) (2018)
- [I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting](https://mlsanity.com/paper/2012.09014/) (2020)
- [Cyclic Differentiable Architecture Search](https://mlsanity.com/paper/2006.10724/) (2020)
- [Incremental Embedding Learning via Zero-Shot Translation](https://mlsanity.com/paper/2012.15497/) (2020)

## Built on by (most cited first, 11 of 11)

- [Never-Ending Behavior-Cloning Agent for Robotic Manipulation](https://mlsanity.com/paper/2403.00336/) (2024)
- [MuseumMaker: Continual Style Customization without Catastrophic Forgetting](https://mlsanity.com/paper/2404.16612/) (2024)
- [Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection](https://mlsanity.com/paper/2409.08388/) (2024)
- [MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction](https://mlsanity.com/paper/2410.06418/) (2024)
- [Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case](https://mlsanity.com/paper/2503.03548/) (2025)
- [Boosting the Class-Incremental Learning in 3D Point Clouds via Zero-Collection-Cost Basic Shape Pre-Training](https://mlsanity.com/paper/2504.08412/) (2025)
- [Learning-Based Biharmonic Augmentation for Point Cloud Classification](https://mlsanity.com/paper/2311.06070/) (2023)
- [ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning](https://mlsanity.com/paper/2409.12326/) (2024)
- [RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Network](https://mlsanity.com/paper/2501.03221/) (2025)
- [CMIP-CIL: A Cross-Modal Benchmark for Image-Point Class Incremental Learning](https://mlsanity.com/paper/2504.08422/) (2025)
- [RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution](https://mlsanity.com/paper/2601.07855/) (2026)

## Abstract (arXiv)

3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D objects cannot change over time in the real-world. This unrealistic assumption may result in significant performance degradation for them to learn new classes of 3D objects consecutively, due to the catastrophic forgetting on old learned classes. Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects. To tackle the above challenges, we develop a novel Incremental 3D Object Recognition Network (i.e., InOR-Net), which could recognize new classes of 3D objects continuously via overcoming the catastrophic forgetting on old classes. Specifically, a category-guided geometric reasoning is proposed to reason local geometric structures with distinctive 3D characteristics of each class by leveraging intrinsic category information. We then propose a novel critic-induced geometric attention mechanism to distinguish which 3D geometric characteristics within each class are beneficial to overcome the catastrophic forgetting on old classes of 3D objects, while preventing the negative influence of useless 3D characteristics. In addition, a dual adaptive fairness compensations strategy is designed to overcome the forgetting brought by class imbalance, by compensating biased weights and predictions of the classifier. Comparison experiments verify the state-of-the-art performance of the proposed InOR-Net model on several public point cloud datasets.