# Focal Loss in 3D Object Detection

arXiv: https://arxiv.org/abs/1809.06065 · HTML: https://mlsanity.com/paper/1809.06065/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Ground-aware Monocular 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2102.00690/) (2021)
- [YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection](https://mlsanity.com/paper/2103.09422/) (2021)
- [PG-RCNN: Semantic Surface Point Generation for 3D Object Detection](https://mlsanity.com/paper/2307.12637/) (2023)
- [Cyclical Focal Loss](https://mlsanity.com/paper/2202.08978/) (2022)
- [Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Training](https://mlsanity.com/paper/2310.00920/) (2023)
- [DuEqNet: Dual-Equivariance Network in Outdoor 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2302.13577/) (2023)
- [A Mallows-like Criterion for Anomaly Detection with Random Forest Implementation](https://mlsanity.com/paper/2405.18932/) (2024)

## Abstract (arXiv)

3D object detection is still an open problem in autonomous driving scenes. When recognizing and localizing key objects from sparse 3D inputs, autonomous vehicles suffer from a larger continuous searching space and higher fore-background imbalance compared to image-based object detection. In this paper, we aim to solve this fore-background imbalance in 3D object detection. Inspired by the recent use of focal loss in image-based object detection, we extend this hard-mining improvement of binary cross entropy to point-cloud-based object detection and conduct experiments to show its performance based on two different 3D detectors: 3D-FCN and VoxelNet. The evaluation results show up to 11.2AP gains through the focal loss in a wide range of hyperparameters for 3D object detection.