TY - JOUR
T1 - Completion-Attention Ladder Network for Few-Shot Underwater Acoustic Recognition
AU - Lingzhi, Xue
AU - Xiangyang, Zeng
AU - Xiang, Yan
AU - Shuang, Yang
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2023/12
Y1 - 2023/12
N2 - Underwater acoustic object recognition is becoming attractive given the critical information available. However, this comes at the expense of large-scale annotated data, which is expensive to collect and annotate. This paper proposes a semi-supervised learning approach of CALNet to recognize insufficient sample underwater acoustic targets. Given this goal, we introduce the CALNet network containing supervised and unsupervised modules. Firstly, we leverage the supervised module to recognize the labeled signals and reduce the dimensional feature extraction of unlabeled samples. Then, the unsupervised network is designed as an auxiliary network to optimize the supervised network, which uses low-dimensional features to restore high-dimensional features of unlabeled samples to enhance the classification ability of the supervised network. We especially introduce ReLU activation function to connect the supervised and unsupervised modules that can help find a balanced relationship between classification and regression tasks for recognizing underwater acoustic signals. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our framework showing that the proposed approach achieves the best recognition accuracy compared with the other approaches with few samples. Moreover, the experimental results can demonstrate the optimal combination of variables for the recognition effect of the proposed method under multiple variables.
AB - Underwater acoustic object recognition is becoming attractive given the critical information available. However, this comes at the expense of large-scale annotated data, which is expensive to collect and annotate. This paper proposes a semi-supervised learning approach of CALNet to recognize insufficient sample underwater acoustic targets. Given this goal, we introduce the CALNet network containing supervised and unsupervised modules. Firstly, we leverage the supervised module to recognize the labeled signals and reduce the dimensional feature extraction of unlabeled samples. Then, the unsupervised network is designed as an auxiliary network to optimize the supervised network, which uses low-dimensional features to restore high-dimensional features of unlabeled samples to enhance the classification ability of the supervised network. We especially introduce ReLU activation function to connect the supervised and unsupervised modules that can help find a balanced relationship between classification and regression tasks for recognizing underwater acoustic signals. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our framework showing that the proposed approach achieves the best recognition accuracy compared with the other approaches with few samples. Moreover, the experimental results can demonstrate the optimal combination of variables for the recognition effect of the proposed method under multiple variables.
KW - Few-shot learning
KW - Semi-supervised learning
KW - Underwater acoustic object recognition
UR - http://www.scopus.com/inward/record.url?scp=85149756341&partnerID=8YFLogxK
U2 - 10.1007/s11063-023-11214-3
DO - 10.1007/s11063-023-11214-3
M3 - 文章
AN - SCOPUS:85149756341
SN - 1370-4621
VL - 55
SP - 9563
EP - 9579
JO - Neural Processing Letters
JF - Neural Processing Letters
IS - 7
ER -