# I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting

arXiv: https://arxiv.org/abs/2012.09014 · HTML: https://mlsanity.com/paper/2012.09014/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2020.

## Built on by (most cited first, 20 of 20)

- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [Class-Incremental Learning for Action Recognition in Videos](https://mlsanity.com/paper/2203.13611/) (2022)
- [Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection](https://mlsanity.com/paper/2112.07241/) (2021)
- [DEJA VU: Continual Model Generalization For Unseen Domains](https://mlsanity.com/paper/2301.10418/) (2023)
- [InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation](https://mlsanity.com/paper/2302.09886/) (2023)
- [Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data](https://mlsanity.com/paper/2304.03980/) (2023)
- [Balanced Residual Distillation Learning for 3D Point Cloud Class-Incremental Semantic Segmentation](https://mlsanity.com/paper/2408.01356/) (2024)
- [Continual learning on 3D point clouds with random compressed rehearsal](https://mlsanity.com/paper/2205.08013/) (2022)
- [LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud](https://mlsanity.com/paper/2206.05927/) (2022)
- [DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection](https://mlsanity.com/paper/2212.02057/) (2022)
- [Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection](https://mlsanity.com/paper/2409.08388/) (2024)
- [PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmark](https://mlsanity.com/paper/2304.06775/) (2023)
- [MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction](https://mlsanity.com/paper/2410.06418/) (2024)
- [CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation](https://mlsanity.com/paper/2502.17429/) (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)
- [ER-FSL: Experience Replay with Feature Subspace Learning for Online Continual Learning](https://mlsanity.com/paper/2407.12279/) (2024)
- [ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning](https://mlsanity.com/paper/2409.12326/) (2024)
- [ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation](https://mlsanity.com/paper/2504.01648/) (2025)
- [CMIP-CIL: A Cross-Modal Benchmark for Image-Point Class Incremental Learning](https://mlsanity.com/paper/2504.08422/) (2025)
- [ReConText3D: Replay-based Continual Text-to-3D Generation](https://mlsanity.com/paper/2604.13730/) (2026)

## Abstract (arXiv)

3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of past 3D object classes when facing the common real-world scenario: new classes of 3D objects arrive in a sequence. Moreover, the performance of advanced approaches degrades dramatically for past learned classes (i.e., catastrophic forgetting), due to the irregular and redundant geometric structures of 3D point cloud data. To address these challenges, we propose a new Incremental 3D Object Learning (i.e., I3DOL) model, which is the first exploration to learn new classes of 3D object continually. Specifically, an adaptive-geometric centroid module is designed to construct discriminative local geometric structures, which can better characterize the irregular point cloud representation for 3D object. Afterwards, to prevent the catastrophic forgetting brought by redundant geometric information, a geometric-aware attention mechanism is developed to quantify the contributions of local geometric structures, and explore unique 3D geometric characteristics with high contributions for classes incremental learning. Meanwhile, a score fairness compensation strategy is proposed to further alleviate the catastrophic forgetting caused by unbalanced data between past and new classes of 3D object, by compensating biased prediction for new classes in the validation phase. Experiments on 3D representative datasets validate the superiority of our I3DOL framework.