A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation

被引:5
|
作者
Lee, Yuan-Hao [1 ]
Yang, Fu-En
Wang, Yu-Chiang Frank
机构
[1] Natl Taiwan Univ, Grad Inst Commun Engn, Taipei, Taiwan
来源
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) | 2022年
关键词
D O I
10.1109/WACV51458.2022.00167
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base classes) with such ground truth information, followed by meta-learning strategies to address the above learning task. When only image-level semantic labels can be observed during both training and testing, it is considered as an even more challenging task of weakly supervised few-shot semantic segmentation. To address this problem, we propose a novel meta-learning framework, which predicts pseudo pixel-level segmentation masks from a limited amount of data and their semantic labels. More importantly, our learning scheme further exploits the produced pixel-level information for query image inputs with segmentation guarantees. Thus, our proposed learning model can be viewed as a pixel-level meta-learner. Through extensive experiments on benchmark datasets, we show that our model achieves satisfactory performances under fully supervised settings, yet performs favorably against state-of-the-art methods under weakly supervised settings.
引用
收藏
页码:1607 / 1617
页数:11
相关论文
共 50 条
  • [1] Weakly Supervised Few-Shot Semantic Segmentation via Pseudo Mask Enhancement and Meta Learning
    Zhang, Man
    Zhou, Yong
    Liu, Bing
    Zhao, Jiaqi
    Yao, Rui
    Shao, Zhiwen
    Zhu, Hancheng
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 7980 - 7991
  • [2] Few-shot Text Steganalysis Based on Attentional Meta-learner
    Wen, Juan
    Zhang, Ziwei
    Yang, Yu
    Xue, Yiming
    PROCEEDINGS OF THE 2022 ACM WORKSHOP ON INFORMATION HIDING AND MULTIMEDIA SECURITY, IH-MMSEC 2022, 2022, : 97 - 106
  • [3] Weakly Supervised Few-Shot Segmentation via Meta-Learning
    Gama, Pedro H. T.
    Oliveira, Hugo
    Marcato Jr, Jose
    dos Santos, Jefersson A.
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 1784 - 1797
  • [4] Weakly-supervised Object Representation Learning for Few-shot Semantic Segmentation
    Ying, Xiaowen
    Li, Xin
    Chuah, Mooi Choo
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, : 1496 - 1505
  • [5] Augmented domain agreement for adaptable Meta-Learner on Few-Shot classification
    Widhianingsih, Tintrim Dwi Ary
    Kang, Dae-Ki
    APPLIED INTELLIGENCE, 2022, 52 (07) : 7037 - 7053
  • [6] Augmented domain agreement for adaptable Meta-Learner on Few-Shot classification
    Tintrim Dwi Ary Widhianingsih
    Dae-Ki Kang
    Applied Intelligence, 2022, 52 : 7037 - 7053
  • [7] Weakly Supervised Semantic Segmentation in Aerial Imagery via Explicit Pixel-Level Constraints
    Zhou, Ruixue
    Zhang, Wenkai
    Yuan, Zhiqiang
    Rong, Xuee
    Liu, Wenjie
    Fu, Kun
    Sun, Xian
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [8] Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation
    Du, Ye
    Fu, Zehua
    Liu, Qingjie
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 4654 - 4669
  • [9] An overview on Meta-learning approaches for Few-shot Weakly-supervised Segmentation
    Gama, Pedro Henrique Targino
    Oliveira, Hugo
    dos Santos, Jefersson A.
    Cesar Jr, Roberto M.
    COMPUTERS & GRAPHICS-UK, 2023, 113 : 77 - 88
  • [10] Meta-learners for few-shot weakly-supervised medical image segmentation
    Oliveira, Hugo
    Gama, Pedro H. T.
    Bloch, Isabelle
    Cesar Jr, Roberto Marcondes
    PATTERN RECOGNITION, 2024, 153