Cargando…
Few-shot learning for joint model in underwater acoustic target recognition
In underwater acoustic target recognition, there is a lack of massive high-quality labeled samples to train robust deep neural networks, and it is difficult to collect and annotate a large amount of base class data in advance unlike the image recognition field. Therefore, conventional few-shot learn...
Autores principales: | Tian, Shengzhao, Bai, Di, Zhou, Junlin, Fu, Yan, Chen, Duanbing |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10579255/ https://www.ncbi.nlm.nih.gov/pubmed/37845288 http://dx.doi.org/10.1038/s41598-023-44641-2 |
Ejemplares similares
-
Deep convolution stack for waveform in underwater acoustic target recognition
por: Tian, Shengzhao, et al.
Publicado: (2021) -
Feature augmentation based on information fusion rectification for few-shot image classification
por: Wang, Hang, et al.
Publicado: (2023) -
FewJoint: few-shot learning for joint dialogue understanding
por: Hou, Yutai, et al.
Publicado: (2022) -
Underwater acoustic target recognition method based on a joint neural network
por: Han, Xing Cheng, et al.
Publicado: (2022) -
Deblurring Ghost Imaging Reconstruction Based on Underwater Dataset Generated by Few-Shot Learning
por: Yang, Xu, et al.
Publicado: (2022)