| Autor: |
Zhipeng Lin, Wenjing Yang, Haotian Wang, Haoang Chi, Long Lan |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Applied Sciences, Vol 14, Iss 16, p 7060 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2076-3417 |
| DOI: |
10.3390/app14167060 |
| Popis: |
Few-shot learning (FSL) is designed to equip models with the capability to quickly adapt to new, unseen domains in open-world scenarios. However, there is a notable discrepancy between the multitude of new concepts encountered in the open world and the limited scale of existing FSL studies, which focus predominantly on a small number of novel classes. This limitation hinders the practical implementation of FSL in real-world situations. To address this issue, we introduce a novel problem called Few-Shot Learning with Many Novel Classes (FSL-MNC), which expands the number of novel classes more than 500 times compared to traditional FSL settings. This new challenge presents two main difficulties: increased computational load during meta-training and reduced classification accuracy due to the larger number of classes during meta-testing. To tackle these problems, we introduce the Simple Hierarchy Pipeline (SHA-Pipeline). In response to the inefficiency of traditional Episode Meta-Learning (EML) protocols, we redesign a more efficient meta-training strategy to manage the increased number of novel classes. Moreover, to distinguish distinct semantic features across a broad array of novel classes, we effectively reconstruct and utilize class hierarchy information during meta-testing. Our experiments demonstrate that the SHA-Pipeline substantially outperforms both the ProtoNet baseline and current leading alternatives across various numbers of novel classes. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
