# Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection

arXiv: https://arxiv.org/abs/2401.05011 · HTML: https://mlsanity.com/paper/2401.05011/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 10 Jan 2024.

## Builds on (most cited first, 19 of 19)

- [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)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2104.09804/) (2021)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding](https://mlsanity.com/paper/2304.06906/) (2023)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds](https://mlsanity.com/paper/2210.04264/) (2022)
- [Semi-supervised 3D Object Detection with Proficient Teachers](https://mlsanity.com/paper/2207.12655/) (2022)
- [Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training](https://mlsanity.com/paper/2107.05031/) (2021)
- [GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation](https://mlsanity.com/paper/2207.02466/) (2022)
- [We don't need no bounding-boxes: Training object class detectors using only human verification](https://mlsanity.com/paper/1602.08405/) (2016)
- [Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation](https://mlsanity.com/paper/1807.06072/) (2018)
- [Semi-supervised Object Detection via Virtual Category Learning](https://mlsanity.com/paper/2207.03433/) (2022)
- [Boosting Semi-Supervised 3D Object Detection with Semi-Sampling](https://mlsanity.com/paper/2211.07084/) (2022)

## Built on by (most cited first, 9 of 9)

- [Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image](https://mlsanity.com/paper/2407.05256/) (2024)
- [Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection](https://mlsanity.com/paper/2503.16125/) (2025)
- [On-the-fly Point Feature Representation for Point Clouds Analysis](https://mlsanity.com/paper/2407.21335/) (2024)
- [CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2603.23276/) (2026)
- [Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments](https://mlsanity.com/paper/2604.07997/) (2026)
- [GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2512.23147/) (2025)
- [PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2604.19379/) (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)

Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing a teacher model to generate pseudo-labels for unlabeled samples. However, the availability of unlabeled samples in the 3D domain is relatively limited compared to its 2D counterpart due to the greater effort required to collect 3D data. Moreover, the loose consistency regularization in SESS and restricted pseudo-label selection strategy in 3DIoUMatch lead to either low-quality supervision or a limited amount of pseudo labels. To address these issues, we present a novel Dual-Perspective Knowledge Enrichment approach named DPKE for semi-supervised 3D object detection. Our DPKE enriches the knowledge of limited training data, particularly unlabeled data, from two perspectives: data-perspective and feature-perspective. Specifically, from the data-perspective, we propose a class-probabilistic data augmentation method that augments the input data with additional instances based on the varying distribution of class probabilities. Our DPKE achieves feature-perspective knowledge enrichment by designing a geometry-aware feature matching method that regularizes feature-level similarity between object proposals from the student and teacher models. Extensive experiments on the two benchmark datasets demonstrate that our DPKE achieves superior performance over existing state-of-the-art approaches under various label ratio conditions. The source code will be made available to the public.