# Delving into the Pre-training Paradigm of Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2206.03657 · HTML: https://mlsanity.com/paper/2206.03657/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 8 Jun 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Deep Layer Aggregation](https://mlsanity.com/paper/1707.06484/) (2017)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving](https://mlsanity.com/paper/2001.03343/) (2020)
- [Delving into Localization Errors for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16237/) (2021)
- [ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape](https://mlsanity.com/paper/1812.02781/) (2018)
- [Rethinking Pseudo-LiDAR Representation](https://mlsanity.com/paper/2008.04582/) (2020)
- [AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2108.11127/) (2021)
- [Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection](https://mlsanity.com/paper/2205.09373/) (2022)

## Built on by (most cited first, 2 of 2)

- [VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection](https://mlsanity.com/paper/2304.01054/) (2023)
- [Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems](https://mlsanity.com/paper/2512.24385/) (2025)

## Abstract (arXiv)

The labels of monocular 3D object detection (M3OD) are expensive to obtain. Meanwhile, there usually exists numerous unlabeled data in practical applications, and pre-training is an efficient way of exploiting the knowledge in unlabeled data. However, the pre-training paradigm for M3OD is hardly studied. We aim to bridge this gap in this work. To this end, we first draw two observations: (1) The guideline of devising pre-training tasks is imitating the representation of the target task. (2) Combining depth estimation and 2D object detection is a promising M3OD pre-training baseline. Afterwards, following the guideline, we propose several strategies to further improve this baseline, which mainly include target guided semi-dense depth estimation, keypoint-aware 2D object detection, and class-level loss adjustment. Combining all the developed techniques, the obtained pre-training framework produces pre-trained backbones that improve M3OD performance significantly on both the KITTI-3D and nuScenes benchmarks. For example, by applying a DLA34 backbone to a naive center-based M3OD detector, the moderate rm AP3D70 score of Car on the KITTI-3D testing set is boosted by 18.71% and the NDS score on the nuScenes validation set is improved by 40.41% relatively.