# Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training

arXiv: https://arxiv.org/abs/2204.11590 · HTML: https://mlsanity.com/paper/2204.11590/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 49 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://mlsanity.com/paper/1907.06038/) (2019)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud](https://mlsanity.com/paper/1903.09847/) (2019)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [AutoDIAL: Automatic DomaIn Alignment Layers](https://mlsanity.com/paper/1704.08082/) (2017)
- [Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency](https://mlsanity.com/paper/2107.11355/) (2021)

## Built on by (most cited first, 22 of 22)

- [GenAD: Generalized Predictive Model for Autonomous Driving](https://mlsanity.com/paper/2403.09630/) (2024)
- [Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2303.01686/) (2023)
- [PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation](https://mlsanity.com/paper/2406.06679/) (2024)
- [Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2410.22461/) (2024)
- [MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection](https://mlsanity.com/paper/2304.02431/) (2023)
- [Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning](https://mlsanity.com/paper/2308.16484/) (2023)
- [Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing](https://mlsanity.com/paper/2310.11346/) (2023)
- [WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detection](https://mlsanity.com/paper/2407.20818/) (2024)
- [Towards Model Generalization for Monocular 3D Object Detection](https://mlsanity.com/paper/2205.11664/) (2022)
- [CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector](https://mlsanity.com/paper/2508.11185/) (2025)
- [BEVUDA: Multi-geometric Space Alignments for Domain Adaptive BEV 3D Object Detection](https://mlsanity.com/paper/2211.17126/) (2022)
- [DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception](https://mlsanity.com/paper/2401.08687/) (2024)
- [MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection](https://mlsanity.com/paper/2510.24688/) (2025)
- [Fully Test-Time Adaptation for Monocular 3D Object Detection](https://mlsanity.com/paper/2405.19682/) (2024)
- [MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models](https://mlsanity.com/paper/2503.13743/) (2025)
- [EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR](https://mlsanity.com/paper/2603.04090/) (2026)
- [LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices](https://mlsanity.com/paper/2209.00961/) (2022)
- [Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection](https://mlsanity.com/paper/2303.11243/) (2023)
- [BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2509.14151/) (2025)
- [LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection](https://mlsanity.com/paper/2512.05663/) (2025)
- [PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2604.19379/) (2026)
- [MAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection](https://mlsanity.com/paper/2608.14282/) (2026)

## Abstract (arXiv)

Monocular 3D object detection (Mono3D) has achieved unprecedented success with the advent of deep learning techniques and emerging large-scale autonomous driving datasets. However, drastic performance degradation remains an unwell-studied challenge for practical cross-domain deployment as the lack of labels on the target domain. In this paper, we first comprehensively investigate the significant underlying factor of the domain gap in Mono3D, where the critical observation is a depth-shift issue caused by the geometric misalignment of domains. Then, we propose STMono3D, a new self-teaching framework for unsupervised domain adaptation on Mono3D. To mitigate the depth-shift, we introduce the geometry-aligned multi-scale training strategy to disentangle the camera parameters and guarantee the geometry consistency of domains. Based on this, we develop a teacher-student paradigm to generate adaptive pseudo labels on the target domain. Benefiting from the end-to-end framework that provides richer information of the pseudo labels, we propose the quality-aware supervision strategy to take instance-level pseudo confidences into account and improve the effectiveness of the target-domain training process. Moreover, the positive focusing training strategy and dynamic threshold are proposed to handle tremendous FN and FP pseudo samples. STMono3D achieves remarkable performance on all evaluated datasets and even surpasses fully supervised results on the KITTI 3D object detection dataset. To the best of our knowledge, this is the first study to explore effective UDA methods for Mono3D.