# Exploring 2D Data Augmentation for 3D Monocular Object Detection

arXiv: https://arxiv.org/abs/2104.10786 · HTML: https://mlsanity.com/paper/2104.10786/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 21 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [Bottom-up Object Detection by Grouping Extreme and Center Points](https://mlsanity.com/paper/1901.08043/) (2019)
- [RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving](https://mlsanity.com/paper/2001.03343/) (2020)
- [ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape](https://mlsanity.com/paper/1812.02781/) (2018)
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://mlsanity.com/paper/1903.10955/) (2019)
- [Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps](https://mlsanity.com/paper/1809.11036/) (2018)
- [Exploring Data Augmentation for Multi-Modality 3D Object Detection](https://mlsanity.com/paper/2012.12741/) (2020)

## Built on by (most cited first, 3 of 3)

- [DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.10758/) (2022)
- [SA-BEV: Generating Semantic-Aware Bird's-Eye-View Feature for Multi-view 3D Object Detection](https://mlsanity.com/paper/2307.11477/) (2023)
- [Diagnosis and Prognosis of Head and Neck Cancer Patients using Artificial Intelligence](https://mlsanity.com/paper/2306.00034/) (2023)

## Abstract (arXiv)

Data augmentation is a key component of CNN based image recognition tasks like object detection. However, it is relatively less explored for 3D object detection. Many standard 2D object detection data augmentation techniques do not extend to 3D box. Extension of these data augmentations for 3D object detection requires adaptation of the 3D geometry of the input scene and synthesis of new viewpoints. This requires accurate depth information of the scene which may not be always available. In this paper, we evaluate existing 2D data augmentations and propose two novel augmentations for monocular 3D detection without a requirement for novel view synthesis. We evaluate these augmentations on the RTM3D detection model firstly due to the shorter training times . We obtain a consistent improvement by 4% in the 3D AP (@IoU=0.7) for cars, ~1.8% scores 3D AP (@IoU=0.25) for pedestrians & cyclists, over the baseline on KITTI car detection dataset. We also demonstrate a rigorous evaluation of the mAP scores by re-weighting them to take into account the class imbalance in the KITTI validation dataset.