Semantic Segmentation with Active Semi-Supervised Learning

被引:6
|
作者
Rangnekar, Aneesh [1 ]
Kanan, Christopher [1 ]
Hoffman, Matthew [1 ]
机构
[1] Rochester Inst Technol, Rochester, NY 14623 USA
关键词
D O I
10.1109/WACV56688.2023.00591
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it would be ideal to minimize the number of human annotations needed when creating a new dataset. Here, we address this problem by proposing a novel algorithm that combines active learning and semi-supervised learning. Active learning is an approach for identifying the best unlabeled samples to annotate. While there has been work on active learning for segmentation, most methods require annotating all pixel objects in each image, rather than only the most informative regions. We argue that this is inefficient. Instead, our active learning approach aims to minimize the number of annotations per-image. Our method is enriched with semi-supervised learning, where we use pseudo labels generated with a teacher-student framework to identify image regions that help disambiguate confused classes. We also integrate mechanisms that enable better performance on imbalanced label distributions, which have not been studied previously for active learning in semantic segmentation. In experiments on the CamVid and CityScapes datasets, our method obtains over 95% of the network's performance on the full-training set using less than 17% of the training data, whereas the previous state of the art required 40% of the training data.
引用
收藏
页码:5955 / 5966
页数:12
相关论文
共 50 条
  • [1] Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images
    Desai, Shasvat
    Ghose, Debasmita
    [J]. 2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, : 1485 - 1495
  • [2] ROBUST ADVERSARIAL LEARNING FOR SEMI-SUPERVISED SEMANTIC SEGMENTATION
    Zhang, Jia
    Li, Zhixin
    Zhang, Canlong
    Ma, Huifang
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 728 - 732
  • [3] Semi-supervised Learning for Segmentation Under Semantic Constraint
    Ganaye, Pierre-Antoine
    Sdika, Michael
    Benoit-Cattin, Hugues
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, PT III, 2018, 11072 : 595 - 602
  • [4] Fuzzy Positive Learning for Semi-supervised Semantic Segmentation
    Qiao, Pengchong
    Wei, Zhidan
    Wang, Yu
    Wang, Zhennan
    Song, Guoli
    Xu, Fan
    Ji, Xiangyang
    Liu, Chang
    Chen, Jie
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 15465 - 15474
  • [5] Semi-supervised Learning Methods for Semantic Segmentation of Polyps
    Ines, Adrian
    Dominguez, Cesar
    Heras, Jonathan
    Mata, Eloy
    Pascual, Vico
    [J]. ADVANCES IN ARTIFICIAL INTELLIGENCE, CAEPIA 2024, 2024, : 162 - 172
  • [6] Transferable Semi-Supervised Semantic Segmentation
    Xiao, Huaxin
    Wei, Yunchao
    Liu, Yu
    Zhang, Maojun
    Feng, Jiashi
    [J]. THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 7420 - 7427
  • [7] Universal Semi-Supervised Semantic Segmentation
    Kalluri, Tarun
    Varma, Girish
    Chandraker, Manmohan
    Jawahar, C. V.
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 5258 - 5269
  • [8] Semantic Equalization Learning for Semi-Supervised SAR Building Segmentation
    Lee, Eungbean
    Jeong, Somi
    Kim, Junhee
    Sohn, Kwanghoon
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [9] A baseline for semi-supervised learning of efficient semantic segmentation models
    Grubisic, Ivan
    Orsic, Marin
    Segvic, Sinisa
    [J]. PROCEEDINGS OF 17TH INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA 2021), 2021,
  • [10] Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
    Hu, Hanzhe
    Wei, Fangyun
    Hu, Han
    Ye, Qiwei
    Cui, Jinshi
    Wang, Liwei
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34