# 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection

arXiv: https://arxiv.org/abs/2012.04355 · HTML: https://mlsanity.com/paper/2012.04355/

## Key facts

- Cited by 89 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 30 of 89)

- [One Million Scenes for Autonomous Driving: ONCE Dataset](https://mlsanity.com/paper/2106.11037/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://mlsanity.com/paper/2303.02314/) (2023)
- [EfficientLPS: Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2102.08009/) (2021)
- [Semi-supervised 3D Object Detection with Proficient Teachers](https://mlsanity.com/paper/2207.12655/) (2022)
- [SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud](https://mlsanity.com/paper/2212.02845/) (2022)
- [Pseudo-labeling for Scalable 3D Object Detection](https://mlsanity.com/paper/2103.02093/) (2021)
- [Learning from Temporal Gradient for Semi-supervised Action Recognition](https://mlsanity.com/paper/2111.13241/) (2021)
- [Multimodal Semi-Supervised Learning for 3D Objects](https://mlsanity.com/paper/2110.11601/) (2021)
- [Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection](https://mlsanity.com/paper/2304.01464/) (2023)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [LEOD: Label-Efficient Object Detection for Event Cameras](https://mlsanity.com/paper/2311.17286/) (2023)
- [Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.04448/) (2022)
- [DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection](https://mlsanity.com/paper/2203.09510/) (2022)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification](https://mlsanity.com/paper/2111.00928/) (2021)
- [DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2303.05079/) (2023)
- [Doubly Robust Self-Training](https://mlsanity.com/paper/2306.00265/) (2023)
- [Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement](https://mlsanity.com/paper/2203.05238/) (2022)
- [Pseudo-label refinement using superpixels for semi-supervised brain tumour segmentation](https://mlsanity.com/paper/2110.08589/) (2021)
- [FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering](https://mlsanity.com/paper/2203.15765/) (2022)
- [DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection](https://mlsanity.com/paper/2304.13031/) (2023)
- [An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds](https://mlsanity.com/paper/2303.12535/) (2023)
- [Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection](https://mlsanity.com/paper/2312.02966/) (2023)
- [Class-Level Confidence Based 3D Semi-Supervised Learning](https://mlsanity.com/paper/2210.10138/) (2022)
- [Commonsense Prototype for Outdoor Unsupervised 3D Object Detection](https://mlsanity.com/paper/2404.16493/) (2024)
- [Self-Distillation for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2210.08226/) (2022)
- [DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets](https://mlsanity.com/paper/2201.08812/) (2022)
- [Semi-supervised 3D Object Detection via Temporal Graph Neural Networks](https://mlsanity.com/paper/2202.00182/) (2022)

## Abstract (arXiv)

3D object detection is an important yet demanding task that heavily relies on difficult to obtain 3D annotations. To reduce the required amount of supervision, we propose 3DIoUMatch, a novel semi-supervised method for 3D object detection applicable to both indoor and outdoor scenes. We leverage a teacher-student mutual learning framework to propagate information from the labeled to the unlabeled train set in the form of pseudo-labels. However, due to the high task complexity, we observe that the pseudo-labels suffer from significant noise and are thus not directly usable. To that end, we introduce a confidence-based filtering mechanism, inspired by FixMatch. We set confidence thresholds based upon the predicted objectness and class probability to filter low-quality pseudo-labels. While effective, we observe that these two measures do not sufficiently capture localization quality. We therefore propose to use the estimated 3D IoU as a localization metric and set category-aware self-adjusted thresholds to filter poorly localized proposals. We adopt VoteNet as our backbone detector on indoor datasets while we use PV-RCNN on the autonomous driving dataset, KITTI. Our method consistently improves state-of-the-art methods on both ScanNet and SUN-RGBD benchmarks by significant margins under all label ratios (including fully labeled setting). For example, when training using only 10% labeled data on ScanNet, 3DIoUMatch achieves 7.7% absolute improvement on mAP@0.25 and 8.5% absolute improvement on mAP@0.5 upon the prior art. On KITTI, we are the first to demonstrate semi-supervised 3D object detection and our method surpasses a fully supervised baseline from 1.8% to 7.6% under different label ratios and categories.