Few-Shot Fine-Grained Image Classification: A Comprehensive Review

被引：10

作者：

Ren, Jie ^{[1
]}

Li, Changmiao ^{[1
]}

An, Yaohui ^{[1
]}

Zhang, Weichuan ^{[2
]}

Sun, Changming ^{[3
]}

机构：

[1] Xian Polytech Univ, Coll Elect & Informat, Xian 710048, Peoples R China

[2] Shaanxi Univ Sci & Technol, Sch Elect Informat & Artificial Intelligence, Xian 710021, Peoples R China

[3] CSIRO Data61, POB 76, Epping, NSW 1710, Australia

来源：

AI | 2024年 / 5卷 / 01期

关键词：

few-shot fine-grained image classification; feature representation learning; meta-learning; metric-learning; NETWORK; ALIGNMENT;

D O I：

10.3390/ai5010020

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 fine-grained image classification (FSFGIC) methods refer to the classification of images (e.g., birds, flowers, and airplanes) belonging to different subclasses of the same species by a small number of labeled samples. Through feature representation learning, FSFGIC methods can make better use of limited sample information, learn more discriminative feature representations, greatly improve the classification accuracy and generalization ability, and thus achieve better results in FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local and/or global deep feature representation learning, class representation learning, and task-specific feature representation learning). In addition, the existing popular datasets, current challenges and future development trends of feature representation learning on FSFGIC are also described.

引用

页码：405 / 425

页数：21

共 134 条

[21] A Two-Stream Network with Image-to-Class Deep Metric for Few-Shot Classification [J].

Gu, Qinghua ;

Luo, Zhengding ;

Zhu, Yuesheng .

ECAI 2020: 24TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, 325 :2704-2711

[22]

Guo YR, 2021, Arxiv, DOI arXiv:2101.09840

[23] Collect and Select: Semantic Alignment Metric Learning for Few-Shot Learning [J].

Hao, Fusheng ;

He, Fengxiang ;

Cheng, Jun ;

Wang, Lei ;

Cao, Jianzhong ;

Tao, Dacheng .

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :8459-8468

[24] CORL: Compositional Representation Learning for Few-Shot Classification [J].

He, Ju ;

Kortylewski, Adam ;

Yuille, Alan .

2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, :3879-3888

[25] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[26]

He X., 2020, arXiv

[27]

He Y., 2022, P IEEE C COMP VIS PA, P9119

[28]

Hilliard N, 2018, Arxiv, DOI arXiv:1802.04376

[29] Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning [J].

Hu, Yuqing ;

Pateux, Stephane ;

Gripon, Vincent .

ALGORITHMS, 2022, 15 (05)

[30] Leveraging the Feature Distribution in Transfer-Based Few-Shot Learning [J].

Hu, Yuqing ;

Gripon, Vincent ;

Pateux, Stephane .

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT II, 2021, 12892 :487-499

← 1 2 3 4 5 6 7 8 9 10 →