Few-Shot Fine-Grained Image Classification: A Comprehensive Review
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/5/1/20 |
| _version_ | 1797242356206927872 |
|---|---|
| author | Jie Ren Changmiao Li Yaohui An Weichuan Zhang Changming Sun |
| author_facet | Jie Ren Changmiao Li Yaohui An Weichuan Zhang Changming Sun |
| author_sort | Jie Ren |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-24T18:37:55Z |
| format | Article |
| id | doaj.art-9db9087c0aa34610a97043e4506c1d1a |
| institution | Directory Open Access Journal |
| issn | 2673-2688 |
| language | English |
| last_indexed | 2024-04-24T18:37:55Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj.art-9db9087c0aa34610a97043e4506c1d1a2024-03-27T13:17:12ZengMDPI AGAI2673-26882024-03-015140542510.3390/ai5010020Few-Shot Fine-Grained Image Classification: A Comprehensive ReviewJie Ren0Changmiao Li1Yaohui An2Weichuan Zhang3Changming Sun4College of Electrical and Information, Xi’an Polytechnic University, Xi’an 710048, ChinaCollege of Electrical and Information, Xi’an Polytechnic University, Xi’an 710048, ChinaCollege of Electrical and Information, Xi’an Polytechnic University, Xi’an 710048, ChinaSchool of Electronic Information and Artificial Intelligence, Shaanxi University of Technology and Science, Xi’an 710021, ChinaCSIRO Data61, P.O. Box 76, Epping, NSW 1710, AustraliaFew-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.https://www.mdpi.com/2673-2688/5/1/20few-shot fine-grained image classificationfeature representation learningmeta-learningmetric-learning |
| spellingShingle | Jie Ren Changmiao Li Yaohui An Weichuan Zhang Changming Sun Few-Shot Fine-Grained Image Classification: A Comprehensive Review AI few-shot fine-grained image classification feature representation learning meta-learning metric-learning |
| title | Few-Shot Fine-Grained Image Classification: A Comprehensive Review |
| title_full | Few-Shot Fine-Grained Image Classification: A Comprehensive Review |
| title_fullStr | Few-Shot Fine-Grained Image Classification: A Comprehensive Review |
| title_full_unstemmed | Few-Shot Fine-Grained Image Classification: A Comprehensive Review |
| title_short | Few-Shot Fine-Grained Image Classification: A Comprehensive Review |
| title_sort | few shot fine grained image classification a comprehensive review |
| topic | few-shot fine-grained image classification feature representation learning meta-learning metric-learning |
| url | https://www.mdpi.com/2673-2688/5/1/20 |
| work_keys_str_mv | AT jieren fewshotfinegrainedimageclassificationacomprehensivereview AT changmiaoli fewshotfinegrainedimageclassificationacomprehensivereview AT yaohuian fewshotfinegrainedimageclassificationacomprehensivereview AT weichuanzhang fewshotfinegrainedimageclassificationacomprehensivereview AT changmingsun fewshotfinegrainedimageclassificationacomprehensivereview |