Feature fusion network based on few-shot fine-grained classification

被引:0
|
作者
Yang, Yajie [1 ]
Feng, Yuxuan [1 ]
Zhu, Li [1 ]
Fu, Haitao [1 ]
Pan, Xin [1 ]
Jin, Chenlei [1 ]
机构
[1] Jilin Agr Univ, Coll Informat Technol, Changchun, Peoples R China
来源
关键词
few-shot classification; fine-grained classification; similarity measurement; inter-class distinctiveness; intra-class compactness;
D O I
10.3389/fnbot.2023.1301192
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where the inter-class distance is small and the intra-class distance is big, relying on a singular similarity measurement can lead to the omission of either inter-class or intra-class information. We delve into inter-class information through global measures and tap into intra-class information via local measures. In this study, we introduce the Feature Fusion Similarity Network (FFSNet). This model employs global measures to accentuate the differences between classes, while utilizing local measures to consolidate intra-class data. Such an approach enables the model to learn features characterized by enlarge inter-class distances and reduce intra-class distances, even with a limited dataset of fine-grained images. Consequently, this greatly enhances the model's generalization capabilities. Our experimental results demonstrated that the proposed paradigm stands its ground against state-of-the-art models across multiple established fine-grained image benchmark datasets.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] Variational Feature Disentangling for Fine-Grained Few-Shot Classification
    Xu, Jingyi
    Le, Hieu
    Huang, Mingzhen
    Athar, ShahRukh
    Samaras, Dimitris
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 8792 - 8801
  • [2] Fine-Grained Few-Shot Image Classification Based on Feature Dual Reconstruction
    Liu, Shudong
    Zhong, Wenlong
    Guo, Furong
    Cong, Jia
    Gu, Boyu
    [J]. ELECTRONICS, 2024, 13 (14)
  • [3] Adaptive Feature Fusion Embedding Network for Few Shot Fine-Grained Image Classification
    Xie, Yaohua
    Zhang, Weichuan
    Ren, Jie
    Jing, Junfeng
    [J]. Computer Engineering and Applications, 2024, 59 (03) : 184 - 192
  • [4] Self-reconstruction network for fine-grained few-shot classification
    Li, Xiaoxu
    Li, Zhen
    Xie, Jiyang
    Yang, Xiaochen
    Xue, Jing-Hao
    Ma, Zhanyu
    [J]. PATTERN RECOGNITION, 2024, 152
  • [5] Few-shot image classification using graph neural network with fine-grained feature descriptors
    Ganesan, Priyanka
    Jagatheesaperumal, Senthil Kumar
    Hassan, Mohammad Mehedi
    Pupo, Francesco
    Fortino, Giancarlo
    [J]. NEUROCOMPUTING, 2024, 610
  • [6] Bi-Directional Ensemble Feature Reconstruction Network for Few-Shot Fine-Grained Classification
    Wu, Jijie
    Chang, Dongliang
    Sain, Aneeshan
    Li, Xiaoxu
    Ma, Zhanyu
    Cao, Jie
    Guo, Jun
    Song, Yi-Zhe
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (09) : 6082 - 6096
  • [7] KNOWLEDGE-BASED FINE-GRAINED CLASSIFICATION FOR FEW-SHOT LEARNING
    Zhao, Jiabao
    Lin, Xin
    Zhou, Jie
    Yang, Jing
    He, Liang
    Yang, Zhaohui
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,
  • [8] Few-Shot Fine-Grained Classification With Rotation-Invariant Feature Map Complementary Reconstruction Network
    Li, Yangfan
    Chen, Liang
    Li, Wei
    Wang, Nan
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 12
  • [9] Few-Shot Fine-Grained Ship Classification With a Foreground-Aware Feature Map Reconstruction Network
    Li, Yangfan
    Bian, Chunjiang
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [10] Feature alignment via mutual mapping for few-shot fine-grained visual classification
    Wu, Qin
    Song, Tingting
    Fan, Shengnan
    Chen, Zeda
    Jin, Kelei
    Zhou, Haojie
    [J]. IMAGE AND VISION COMPUTING, 2024, 147