Context-Aware Multi-Task Learning for Traffic Scene Recognition in Autonomous Vehicles

被引:0
|
作者
Lee, Younkwan [1 ]
Jeon, Jihyo [1 ]
Yu, Jongmin [1 ,2 ]
Jeon, Moongu [1 ]
机构
[1] Gwangju Inst Sci & Technol GIST, Machine Learning & Vis Lab, Gwangju 61005, South Korea
[2] Curtin Univ, Bentley, WA 6102, Australia
基金
新加坡国家研究基金会;
关键词
CLASSIFICATION; TIME; FEATURES; SPACE;
D O I
10.1109/iv47402.2020.9304708
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the entire system as a whole. Because of this, they are limited to utilizing a task-specific set of features for all possible tasks of inference-time, which ignores the capability to leverage common task-invariant contextual knowledge for the task at hand. To address this problem, we propose an algorithm to jointly learn the task-specific and shared representations by adopting a multi-task learning network. Specifically, we present a lower bound for the mutual information constraint between shared feature embedding and input that is considered to be able to extract common contextual information across tasks while preserving essential information of each task jointly. The learned representations capture richer contextual information without additional task-specific network. Extensive experiments on the large-scale dataset HSD demonstrate the effectiveness and superiority of our network over state-of-the-art methods.
引用
收藏
页码:723 / 730
页数:8
相关论文
共 50 条
  • [1] Research on Road Scene Understanding of Autonomous Vehicles Based on Multi-Task Learning
    Guo, Jinghua
    Wang, Jingyao
    Wang, Huinian
    Xiao, Baoping
    He, Zhifei
    Li, Lubin
    [J]. SENSORS, 2023, 23 (13)
  • [2] Scene text recognition with context-aware autonomous bidirectional iterative models
    Zhao, Xiaoqing
    Xu, Miaomiao
    Li, Yanbing
    Huang, Hao
    Silamu, Wushour
    [J]. Journal of Intelligent and Fuzzy Systems, 2024, 46 (04): : 8605 - 8616
  • [3] Scene recognition under special traffic conditions based on deep multi-task learning
    Hu, Xiaochang
    Xu, Xin
    Xiao, Yongqian
    Chen, Hongjun
    Zhang, Hongjia
    [J]. JOURNAL OF ENGINEERING-JOE, 2020, 2020 (13): : 471 - 475
  • [4] Situation Aware Multi-Task Learning for Traffic Prediction
    Deng, Dingxiong
    Shahabi, Cyrus
    Demiryurek, Ugur
    Zhu, Linhong
    [J]. 2017 17TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2017, : 81 - 90
  • [5] Learning Context-aware Policies from Multiple Smart Homes via Federated Multi-Task Learning
    Yu, Tianlong
    Li, Tian
    Sun, Yuqiong
    Nanda, Susanta
    Smith, Virginia
    Sekar, Vyas
    Seshan, Srinivasan
    [J]. 2020 ACM/IEEE FIFTH INTERNATIONAL CONFERENCE ON INTERNET OF THINGS DESIGN AND IMPLEMENTATION (IOTDI 2020), 2020, : 104 - 115
  • [6] DeepApp: Predicting Personalized Smartphone App Usage via Context-Aware Multi-Task Learning
    Xia, Tong
    Li, Yong
    Feng, Jie
    Jin, Depeng
    Zhang, Qing
    Luo, Hengliang
    Liao, Qingmin
    [J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2020, 11 (06)
  • [7] DeepApp: Predicting Personalized Smartphone App Usage via Context-Aware Multi-Task Learning
    Xia, Tong
    Li, Yong
    Feng, Jie
    Jin, Depeng
    Zhang, Qing
    Luo, Hengliang
    Liao, Qingmin
    [J]. ACM Transactions on Intelligent Systems and Technology, 2020, 11 (06):
  • [8] Traffic Sign Recognition Using Multi-Task Deep Learning for Self-Driving Vehicles
    Alawaji, Khaldaa
    Hedjar, Ramdane
    Zuair, Mansour
    [J]. SENSORS, 2024, 24 (11)
  • [9] Improving User Environment Detection Using Context-Aware Multi-Task Deep Learning in Mobile Networks
    Morel, Marie Line Alberi
    Saffar, Illyyne
    Singh, Kamal
    Hamideche, Sid Ali
    Viho, Cesar
    [J]. IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2022, 8 (04) : 1665 - 1676
  • [10] Pallet Recognition with Multi-Task Learning for Automated Guided Vehicles
    Mok, Chunghyup
    Baek, Insung
    Cho, Yoon Sang
    Kim, Younghoon
    Kim, Seoung Bum
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (24):