Focal Loss in 3D Object Detection

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 let...

Full description

Saved in:
Bibliographic Details
Published in:IEEE robotics and automation letters Vol. 4; no. 2; pp. 1263 - 1270
Main Authors: Yun, Peng, Tai, Lei, Wang, Yuan, Liu, Chengju, Liu, Ming
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.04.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Cameras
Convolution
Deep Learning in Robotics and Automation
Detectors
Entropy
Feature extraction
Image detection
Meteorological satellites
Object detection
Object recognition
Recognition
Segmentation and Categorization
Three-dimensional displays
Two dimensional displays
ISSN:2377-3766, 2377-3766
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 letter, 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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2019.2894858