Adaptive Learning via a Negative Selection Strategy for Few-Shot Bioacoustic Event Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913513529671680 |
|---|---|
| author | Chen, Yaxiong Zhang, Xueping Zi, Yunfei Xiong, Shengwu |
| author_facet | Chen, Yaxiong Zhang, Xueping Zi, Yunfei Xiong, Shengwu |
| contents | Although the Prototypical Network (ProtoNet) has demonstrated effectiveness in few-shot biological event detection, two persistent issues remain. Firstly, there is difficulty in constructing a representative negative prototype due to the absence of explicitly annotated negative samples. Secondly, the durations of the target biological vocalisations vary across tasks, making it challenging for the model to consistently yield optimal results across all tasks. To address these issues, we propose a novel adaptive learning framework with an adaptive learning loss to guide classifier updates. Additionally, we propose a negative selection strategy to construct a more representative negative prototype for ProtoNet. All experiments ware performed on the DCASE 2023 TASK5 few-shot bioacoustic event detection dataset. The results show that our proposed method achieves an F-measure of 0.703, an improvement of 12.84%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15168 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Learning via a Negative Selection Strategy for Few-Shot Bioacoustic Event Detection Chen, Yaxiong Zhang, Xueping Zi, Yunfei Xiong, Shengwu Sound Audio and Speech Processing Although the Prototypical Network (ProtoNet) has demonstrated effectiveness in few-shot biological event detection, two persistent issues remain. Firstly, there is difficulty in constructing a representative negative prototype due to the absence of explicitly annotated negative samples. Secondly, the durations of the target biological vocalisations vary across tasks, making it challenging for the model to consistently yield optimal results across all tasks. To address these issues, we propose a novel adaptive learning framework with an adaptive learning loss to guide classifier updates. Additionally, we propose a negative selection strategy to construct a more representative negative prototype for ProtoNet. All experiments ware performed on the DCASE 2023 TASK5 few-shot bioacoustic event detection dataset. The results show that our proposed method achieves an F-measure of 0.703, an improvement of 12.84%. |
| title | Adaptive Learning via a Negative Selection Strategy for Few-Shot Bioacoustic Event Detection |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.15168 |