Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929383203143680 |
|---|---|
| author | Si, Yongjie Li, Yanxiong Li, Jialong Tan, Jiaxin He, Qianhua |
| author_facet | Si, Yongjie Li, Yanxiong Li, Jialong Tan, Jiaxin He, Qianhua |
| contents | It's assumed that training data is sufficient in base session of few-shot class-incremental audio classification. However, it's difficult to collect abundant samples for model training in base session in some practical scenarios due to the data scarcity of some classes. This paper explores a new problem of fully few-shot class-incremental audio classification with few training samples in all sessions. Moreover, we propose a method using expandable dual-embedding extractor to solve it. The proposed model consists of an embedding extractor and an expandable classifier. The embedding extractor consists of a pretrained Audio Spectrogram Transformer (AST) and a finetuned AST. The expandable classifier consists of prototypes and each prototype represents a class. Experiments are conducted on three datasets (LS-100, NSynth-100 and FSC-89). Results show that our method exceeds seven baseline ones in average accuracy with statistical significance. Code is at: https://github.com/YongjieSi/EDE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08122 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor Si, Yongjie Li, Yanxiong Li, Jialong Tan, Jiaxin He, Qianhua Audio and Speech Processing Sound It's assumed that training data is sufficient in base session of few-shot class-incremental audio classification. However, it's difficult to collect abundant samples for model training in base session in some practical scenarios due to the data scarcity of some classes. This paper explores a new problem of fully few-shot class-incremental audio classification with few training samples in all sessions. Moreover, we propose a method using expandable dual-embedding extractor to solve it. The proposed model consists of an embedding extractor and an expandable classifier. The embedding extractor consists of a pretrained Audio Spectrogram Transformer (AST) and a finetuned AST. The expandable classifier consists of prototypes and each prototype represents a class. Experiments are conducted on three datasets (LS-100, NSynth-100 and FSC-89). Results show that our method exceeds seven baseline ones in average accuracy with statistical significance. Code is at: https://github.com/YongjieSi/EDE. |
| title | Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2406.08122 |