Few-shot Learning: Methods and Applications
The Few-shot learning (FSL) approach distills meaningful features from a constrained sample set, allowing models to swiftly adjust to novel tasks and decreasing the dependency on extensive datasets. This approach leverages methods involving meta-learning, transfer learning, and data augmentation to...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02012.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206599626522624 |
|---|---|
| author | Li Jiaxiang Li Mingyang |
| author_facet | Li Jiaxiang Li Mingyang |
| author_sort | Li Jiaxiang |
| collection | DOAJ |
| description | The Few-shot learning (FSL) approach distills meaningful features from a constrained sample set, allowing models to swiftly adjust to novel tasks and decreasing the dependency on extensive datasets. This approach leverages methods involving meta-learning, transfer learning, and data augmentation to boost the model's ability to recognize new categories. In many areas of artificial intelligence, obtaining large annotated datasets is often high in financial demand and extensively time-consuming, particularly in specialized fields with limited data availability. Therefore, the study of FSL is particularly critical. This paper first reviews the relevant methods of FSL, primarily categorizing them into model fine-tuning based FSL, data augmentation-based FSL, and transfer learning-based FSL. Model fine-tuning based FSL involves making slight adjustments to pre-trained models, allowing them to adapt to new tasks. Data augmentation-based FSL enhances the model's generalization ability by generating or expanding existing data. Transfer learning-based FSL transfers knowledge acquired by models from large datasets to smaller ones, enhancing the learning outcomes. Subsequently, this paper reviews the application areas of FSL and explores its impact in these fields. This paper aims to present the current state and prospects of this technique, providing valuable insights for researchers in related fields. |
| format | Article |
| id | doaj-art-d928aa98e43b44e98aa35486ca194375 |
| institution | Kabale University |
| issn | 2271-2097 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj-art-d928aa98e43b44e98aa35486ca1943752025-02-07T08:21:10ZengEDP SciencesITM Web of Conferences2271-20972025-01-01700201210.1051/itmconf/20257002012itmconf_dai2024_02012Few-shot Learning: Methods and ApplicationsLi Jiaxiang0Li Mingyang1Middle School Affiliated To Renmin University of China Tongzhou CampusShool of Computer and Artificial Intelligence, Beijing Technology and Business UniversityThe Few-shot learning (FSL) approach distills meaningful features from a constrained sample set, allowing models to swiftly adjust to novel tasks and decreasing the dependency on extensive datasets. This approach leverages methods involving meta-learning, transfer learning, and data augmentation to boost the model's ability to recognize new categories. In many areas of artificial intelligence, obtaining large annotated datasets is often high in financial demand and extensively time-consuming, particularly in specialized fields with limited data availability. Therefore, the study of FSL is particularly critical. This paper first reviews the relevant methods of FSL, primarily categorizing them into model fine-tuning based FSL, data augmentation-based FSL, and transfer learning-based FSL. Model fine-tuning based FSL involves making slight adjustments to pre-trained models, allowing them to adapt to new tasks. Data augmentation-based FSL enhances the model's generalization ability by generating or expanding existing data. Transfer learning-based FSL transfers knowledge acquired by models from large datasets to smaller ones, enhancing the learning outcomes. Subsequently, this paper reviews the application areas of FSL and explores its impact in these fields. This paper aims to present the current state and prospects of this technique, providing valuable insights for researchers in related fields.https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02012.pdf |
| spellingShingle | Li Jiaxiang Li Mingyang Few-shot Learning: Methods and Applications ITM Web of Conferences |
| title | Few-shot Learning: Methods and Applications |
| title_full | Few-shot Learning: Methods and Applications |
| title_fullStr | Few-shot Learning: Methods and Applications |
| title_full_unstemmed | Few-shot Learning: Methods and Applications |
| title_short | Few-shot Learning: Methods and Applications |
| title_sort | few shot learning methods and applications |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02012.pdf |
| work_keys_str_mv | AT lijiaxiang fewshotlearningmethodsandapplications AT limingyang fewshotlearningmethodsandapplications |