Few-shot Classification via Ensemble Learning with Multi-Order Statistics

被引:0
|
作者
Yang, Sai [1 ]
Liu, Fan [2 ,3 ]
Chen, Delong [2 ]
Zhou, Jun [4 ]
机构
[1] Nantong Univ, Sch Elect Engn, Nantong, Peoples R China
[2] Hohai Univ, Coll Comp & Informat, Nanjing, Peoples R China
[3] Harbin Engn Univ, Sci & Technol Underwater Vehicle Technol Lab, Harbin, Peoples R China
[4] Griffith Univ, Sch Informat & Commun Technol, Nathan, Qld, Australia
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Transfer learning has been widely adopted for few-shot classification. Recent studies reveal that obtaining good generalization representation of images on novel classes is the key to improving the few-shot classification accuracy. To address this need, we prove theoretically that leveraging ensemble learning on the base classes can correspondingly reduce the true error in the novel classes. Following this principle, a novel method named Ensemble Learning with Multi-Order Statistics (ELMOS) is proposed in this paper. In this method, after the backbone network, we use multiple branches to create the individual learners in the ensemble learning, with the goal to reduce the storage cost. We then introduce different order statistics pooling in each branch to increase the diversity of the individual learners. The learners are optimized with supervised losses during the pre-training phase. After pre-training, features from different branches are concatenated for classifier evaluation. Extensive experiments demonstrate that each branch can complement the others and our method can produce a state-of-the-art performance on multiple few-shot classification benchmark datasets.
引用
收藏
页码:1631 / 1639
页数:9
相关论文
共 50 条
  • [21] Few-shot learning for short text classification
    Yan, Leiming
    Zheng, Yuhui
    Cao, Jie
    MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (22) : 29799 - 29810
  • [22] Few-Shot Learning for Issue Report Classification
    Colavito, Giuseppe
    Lanubile, Filippo
    Novielli, Nicole
    2023 IEEE/ACM 2ND INTERNATIONAL WORKSHOP ON NATURAL LANGUAGE-BASED SOFTWARE ENGINEERING, NLBSE, 2023, : 16 - 19
  • [23] Few-shot learning for short text classification
    Leiming Yan
    Yuhui Zheng
    Jie Cao
    Multimedia Tools and Applications, 2018, 77 : 29799 - 29810
  • [24] Dense Classification and Implanting for Few-Shot Learning
    Lifchitz, Yann
    Avrithis, Yannis
    Picard, Sylvaine
    Bursuc, Andrei
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 9250 - 9259
  • [25] Diversified Contrastive Learning For Few-Shot Classification
    Lu, Guangtong
    Li, Fanzhang
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT I, 2023, 14254 : 147 - 158
  • [26] Integrative Few-Shot Learning for Classification and Segmentation
    Kang, Dahyun
    Cho, Minsu
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 9969 - 9980
  • [27] Visual Classification of Malware by Few-shot Learning
    Tran, Kien
    Kubo, Masao
    Sato, Hiroshi
    PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON ARTIFICIAL LIFE AND ROBOTICS (ICAROB2020), 2020, : 770 - 774
  • [28] Few-Shot Learning for Medical Image Classification
    Cai, Aihua
    Hu, Wenxin
    Zheng, Jun
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT I, 2020, 12396 : 441 - 452
  • [29] Spatial Contrastive Learning for Few-Shot Classification
    Ouali, Yassine
    Hudelot, Celine
    Tami, Myriam
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, 2021, 12975 : 671 - 686
  • [30] Continual Few-Shot Learning for Text Classification
    Pasunuru, Ramakanth
    Stoyanov, Veselin
    Bansal, Mohit
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 5688 - 5702