# Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection

arXiv: https://arxiv.org/abs/2112.07241 · HTML: https://mlsanity.com/paper/2112.07241/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 14 Dec 2021.

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

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [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)
- [Incremental Learning Techniques for Semantic Segmentation](https://mlsanity.com/paper/1907.13372/) (2019)
- [Fast Point R-CNN](https://mlsanity.com/paper/1908.02990/) (2019)
- [Vehicle Detection from 3D Lidar Using Fully Convolutional Network](https://mlsanity.com/paper/1608.07916/) (2016)
- [CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2012.03015/) (2020)
- [Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN](https://mlsanity.com/paper/2003.03901/) (2020)
- [BirdNet: a 3D Object Detection Framework from LiDAR information](https://mlsanity.com/paper/1805.01195/) (2018)
- [I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting](https://mlsanity.com/paper/2012.09014/) (2020)

## Built on by (most cited first, 16 of 16)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [LW2G: Learning Whether to Grow for Prompt-based Continual Learning](https://mlsanity.com/paper/2409.18860/) (2024)
- [Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection](https://mlsanity.com/paper/2503.16125/) (2025)
- [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)
- [UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit Representation](https://mlsanity.com/paper/2212.10950/) (2022)
- [I3DOD: Towards Incremental 3D Object Detection via Prompting](https://mlsanity.com/paper/2308.12512/) (2023)
- [On-the-fly Point Feature Representation for Point Clouds Analysis](https://mlsanity.com/paper/2407.21335/) (2024)
- [MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Construction](https://mlsanity.com/paper/2410.06418/) (2024)
- [Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems](https://mlsanity.com/paper/2508.11679/) (2025)
- [Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments](https://mlsanity.com/paper/2604.07997/) (2026)
- [Ranking-aware Continual Learning for LiDAR Place Recognition](https://mlsanity.com/paper/2505.07198/) (2025)
- [ReConText3D: Replay-based Continual Text-to-3D Generation](https://mlsanity.com/paper/2604.13730/) (2026)
- [Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection](https://mlsanity.com/paper/2607.14560/) (2026)
- [Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training](https://mlsanity.com/paper/2608.19973/) (2026)

## Abstract (arXiv)

Deep learning-based approaches have shown remarkable performance in the 3D object detection task. However, they suffer from a catastrophic performance drop on the originally trained classes when incrementally learning new classes without revisiting the old data. This "catastrophic forgetting" phenomenon impedes the deployment of 3D object detection approaches in real-world scenarios, where continuous learning systems are needed. In this paper, we study the unexplored yet important class-incremental 3D object detection problem and present the first solution - SDCoT, a novel static-dynamic co-teaching method. Our SDCoT alleviates the catastrophic forgetting of old classes via a static teacher, which provides pseudo annotations for old classes in the new samples and regularizes the current model by extracting previous knowledge with a distillation loss. At the same time, SDCoT consistently learns the underlying knowledge from new data via a dynamic teacher. We conduct extensive experiments on two benchmark datasets and demonstrate the superior performance of our SDCoT over baseline approaches in several incremental learning scenarios.