Robust object detection for autonomous driving based on semi-supervised learning

被引:0
|
作者
Wenwen Chen [1 ]
Jun Yan [1 ]
Weiquan Huang [1 ]
Wancheng Ge [1 ]
Huaping Liu [2 ]
Huilin Yin [1 ]
机构
[1] College of Electronic and Information Engineering, Tongji University
[2] School of Electrical Engineering and Computer Science, Oregon State
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论]; TP391.41 []; U463.6 [电气设备及附件];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ; 080203 ;
摘要
Deep learning based on labeled data has brought massive success in computer vision, speech recognition, and natural language processing. Nevertheless, labeled data is just a drop in the ocean compared with unlabeled data. How can people utilize the unlabeled data efectively? Research has focused on unsupervised and semi-supervised learning to solve such a problem. Some theoretical and empirical studies have proved that unlabeled data can help boost the generalization ability and robustness under adversarial attacks. However, current theoretical research on the relationship between robustness and unlabeled data limits its scope to toy datasets. Meanwhile, the visual models in autonomous driving need a significant improvement in robustness to guarantee security and safety. This paper proposes a semi-supervised learning framework for object detection in autonomous vehicles, improving the robustness with unlabeled data. Firstly, we build a baseline with the transfer learning of an unsupervised contrastive learning method—Momentum Contrast(MoCo). Secondly,we propose a semi-supervised co-training method to label the unlabeled data for retraining,which improves generalization on the autonomous driving dataset. Thirdly, we apply the unsupervised Bounding Box data augmentation(BBAug) method based on a search algorithm, which uses reinforcement learning to improve the robustness of object detection for autonomous driving. We present an empirical study on the KITTI dataset with diverse adversarial attack methods. Our proposed method realizes the state-of-the-art generalization and robustness under white-box attacks(DPatch and Contextual Patch) and black-box attacks(Gaussian noise, Rain, Fog, and so on). Our proposed method and empirical study show that using more unlabeled data benefits the robustness of perception systems in autonomous driving.
引用
收藏
页码:18 / 43
页数:26
相关论文
共 50 条
  • [1] Important Object Identification with Semi-Supervised Learning for Autonomous Driving
    Li, Jiachen
    Gang, Haiming
    Ma, Hengbo
    Tomizuka, Masayoshi
    Choi, Chiho
    2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022), 2022, : 2913 - 2919
  • [2] PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems
    Hu, Shu
    Liu, Chun-Hao
    Dutta, Jayanta
    Chang, Ming-Ching
    Lyu, Siwei
    Ramakrishnan, Naveen
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 4389 - 4397
  • [3] A semi-supervised 3D object detection method for autonomous driving
    Zhang, Jiacheng
    Liu, Huafeng
    Lu, Jianfeng
    DISPLAYS, 2022, 71
  • [4] Dense Learning based Semi-Supervised Object Detection
    Chen, Binghui
    Li, Pengyu
    Chen, Xiang
    Wang, Biao
    Zhang, Lei
    Hua, Xian-Sheng
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 4805 - 4814
  • [5] Semi-Supervised Active Learning for Object Detection
    Chen, Sijin
    Yang, Yingyun
    Hua, Yan
    ELECTRONICS, 2023, 12 (02)
  • [6] Consistency-based Semi-supervised Learning for Object Detection
    Jeong, Jisoo
    Lee, Seungeui
    Kim, Jeesoo
    Kwak, Nojun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [7] Interpolation-based Semi-supervised Learning for Object Detection
    Jeong, Jisoo
    Verma, Vikas
    Hyun, Minsung
    Kannala, Juho
    Kwak, Nojun
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 11597 - 11606
  • [8] Proposal Learning for Semi-Supervised Object Detection
    Tang, Peng
    Ramaiah, Chetan
    Wang, Yan
    Xu, Ran
    Xiong, Caiming
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 2290 - 2300
  • [9] Dense Information Learning Based Semi-Supervised Object Detection
    Yang, Xi
    Li, Penghui
    Zhou, Qiubai
    Wang, Nannan
    Gao, Xinbo
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2025, 34 : 1022 - 1035
  • [10] Semi-supervised learning based object detection in aerial imagery
    Yao, J
    Zhang, ZF
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol 1, Proceedings, 2005, : 1011 - 1016