On Power Jaccard Losses for Semantic Segmentation

被引:20
|
作者
Duque-Arias, David [1 ]
Velasco-Forero, Santiago [1 ]
Deschaud, Jean-Emmanuel [1 ]
Goulette, Francois [1 ]
Serna, Andres [2 ]
Decenciere, Etienne [1 ]
Marcotegui, Beatriz [1 ]
机构
[1] PSL Res Univ, MINES ParisTech, Paris, France
[2] Terra3D Res, Paris, France
关键词
Loss Functions; Image Segmentation; Jaccard Loss; Deep Learning; U-Net Architecture;
D O I
10.5220/0010304005610568
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, a new generalized loss function is proposed called power Jaccard to perform semantic segmentation tasks. It is compared with classical loss functions in different scenarios, including gray level and color image segmentation, as well as 3D point cloud segmentation. The results show improved performance, stability and convergence. We made available the code with our proposal with a demonstrative example.
引用
收藏
页码:561 / 568
页数:8
相关论文
共 50 条
  • [41] Autofocus Layer for Semantic Segmentation
    Qin, Yao
    Kamnitsas, Konstantinos
    Ancha, Siddharth
    Nanavati, Jay
    Cottrell, Garrison
    Criminisi, Antonio
    Nori, Aditya
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, PT III, 2018, 11072 : 603 - 611
  • [42] Omnisupervised Omnidirectional Semantic Segmentation
    Yang, Kailun
    Hu, Xinxin
    Fang, Yicheng
    Wang, Kaiwei
    Stiefelhagen, Rainer
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (02) : 1184 - 1199
  • [43] Segmenter: Transformer for Semantic Segmentation
    Strudel, Robin
    Garcia, Ricardo
    Laptev, Ivan
    Schmid, Cordelia
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 7242 - 7252
  • [44] Sparse Dictionaries for Semantic Segmentation
    Tao, Lingling
    Porikli, Fatih
    Vidal, Rene
    COMPUTER VISION - ECCV 2014, PT V, 2014, 8693 : 549 - 564
  • [45] Progressive Adversarial Semantic Segmentation
    Imran, Abdullah-Al-Zubaer
    Terzopoulos, Demetri
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 4910 - 4917
  • [46] DENSE CONVOLUTION FOR SEMANTIC SEGMENTATION
    Han, Chaoyi
    Tao, Xiaoming
    Duan, Yiping
    Lu, Jianhua
    2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 2222 - 2226
  • [47] Averse Deep Semantic Segmentation
    Cruz, Ricardo
    Costa, Joaquim F. Pinto
    Cardoso, Jaime S.
    2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 44 - 47
  • [48] Semantic Segmentation in Compressed Videos
    Li, Ang
    Lu, Yiwei
    Wang, Yang
    2019 IEEE 21ST INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP 2019), 2019,
  • [49] Understanding Convolution for Semantic Segmentation
    Wang, Panqu
    Chen, Pengfei
    Yuan, Ye
    Liu, Ding
    Huang, Zehua
    Hou, Xiaodi
    Cottrell, Garrison
    2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, : 1451 - 1460
  • [50] An Efficient Approach to Semantic Segmentation
    Gabriela Csurka
    Florent Perronnin
    International Journal of Computer Vision, 2011, 95 : 198 - 212