CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 深度强化学习
Multi-task learning with Cartesianproduct-based multi-objective combination fordangerous object detection
Yaran Chen1,2; Dongbin Zhao1,2
Source PublicationPart of the Lecture Notes in Computer Science book series (LNCS, volume 10261)
       Autonomous driving has caused extensively attention of academia and industry. Vision-based dangerous object detection is a crucial technology of autonomous driving which detects object and assesses its danger with distance to warn drivers. Previous vision-based dangerous object detections apply two independent models to deal with object detection and distance prediction, respectively. In this paper, we show that object detection and distance prediction have visual relationship, and they can be improved by exploiting the relationship. We jointly optimize object detection and distance prediction with a novel multi-task learning (MTL) model for using the relationship. In contrast to traditional MTL which uses linear multi-task combination strategy, we propose a Cartesian product-based multi-target combination strategy for MTL to consider the dependent among tasks. The proposed novel MTL method outperforms than the traditional MTL and single task methods by a series of experiments. 
Multi-task Learning with Cartesian Product-Based Multi-objective Combination for Dangerous Object Detection. Available from: [accessed Dec 31 2017].
KeywordDangerous Object Detection Multi-task Learning Convolutional Neural Network
Document Type会议论文
Affiliation1.The State Key Laboratory of Management and Control for Complex Systems, Institute of AutomationChinese Academy of SciencesBeijingChina
2.The University of Chinese Academy of SciencesBeijingChina
Recommended Citation
GB/T 7714
Yaran Chen,Dongbin Zhao. Multi-task learning with Cartesianproduct-based multi-objective combination fordangerous object detection[C],2017:28–35.
Files in This Item: Download All
File Name/Size DocType Version Access License
ISNN.pdf(751KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yaran Chen]'s Articles
[Dongbin Zhao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yaran Chen]'s Articles
[Dongbin Zhao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yaran Chen]'s Articles
[Dongbin Zhao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ISNN.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.