Focal Loss in 3D Object Detection

被引：39
|
作者：
Yun, Peng [1 ]
Tai, Lei [2 ]
Wang, Yuan [2 ]
Liu, Chengju [3 ]
Liu, Ming [2 ]
机构：
[1] Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Hong Kong, Peoples R China
[2] Hong Kong Univ Sci & Technol, Dept Elect & Comp Engn, Hong Kong, Peoples R China
[3] Tongji Univ, Coll Elect & Informat Engn, Shanghai 201804, Peoples R China
来源：
IEEE ROBOTICS AND AUTOMATION LETTERS | 2019年 / 4卷 / 02期
基金：
中国国家自然科学基金;
关键词：
Deep Learning in Robotics and Automation; Object Detection; Segmentation and Categorization; Recognition;
D O I：
10.1109/LRA.2019.2894858
中图分类号：
TP24 [机器人技术];
学科分类号：
080202 ; 1405 ;
摘要：
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 showits 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.
引用
收藏
页码：1263 / 1270
页数：8
相关论文
共 50 条
  • [1] Focal Sparse Convolutional Networks for 3D Object Detection
    Chen, Yukang
    Li, Yanwei
    Zhang, Xiangyu
    Sun, Jian
    Jia, Jiaya
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 5418 - 5427
  • [2] Homography Loss for Monocular 3D Object Detection
    Gu, Jiaqi
    Wu, Bojian
    Fan, Lubin
    Huang, Jianqiang
    Cao, Shen
    Xiang, Zhiyu
    Hua, Xian-Sheng
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1070 - 1079
  • [3] IoU Loss for 2D/3D Object Detection
    Zhou, Dingfu
    Fang, Jin
    Song, Xibin
    Guan, Chenye
    Yin, Junbo
    Dai, Yuchao
    Yang, Ruigang
    2019 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2019), 2019, : 85 - 94
  • [4] Distilling Focal Knowledge from Imperfect Expert for 3D Object Detection
    Zeng, Jia
    Chen, Li
    Deng, Hanming
    Lu, Lewei
    Yan, Junchi
    Qiao, Yu
    Li, Hongyang
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 992 - 1001
  • [5] Improving 3D Object Detection via Joint Attribute-oriented 3D Loss
    Ye, Zhen
    Xue, Jianru
    Dou, Jian
    Pan, Yuxin
    Fang, Jianwu
    Wang, Di
    Zheng, Nanning
    2020 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2020, : 951 - 956
  • [6] Addressing the Gaps of IoU Loss in 3D Object Detection with IIoU
    Ravi, Niranjan
    El-Sharkawy, Mohamed
    FUTURE INTERNET, 2023, 15 (12)
  • [7] Focal Loss for Dense Object Detection
    Lin, Tsung-Yi
    Goyal, Priya
    Girshick, Ross
    He, Kaiming
    Dollar, Piotr
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 2999 - 3007
  • [8] Focal Loss for Dense Object Detection
    Lin, Tsung-Yi
    Goyal, Priya
    Girshick, Ross
    He, Kaiming
    Dollar, Piotr
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 42 (02) : 318 - 327
  • [9] 3D Object Detection with Pointformer
    Pan, Xuran
    Xia, Zhuofan
    Song, Shiji
    Li, Li Erran
    Huang, Gao
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 7459 - 7468
  • [10] A survey of 3D object detection
    Wei Liang
    Pengfei Xu
    Ling Guo
    Heng Bai
    Yang Zhou
    Feng Chen
    Multimedia Tools and Applications, 2021, 80 : 29617 - 29641
12345