The intrinsic complexity associated with passive sonar data makes the task of target recognition extremely challenging. The conventional classifier architectures based on hand-engineered feature transforms often fail miserably to disentangle the high-dimensional non-linear structures in the observed target records. Although the modern deep learning algorithms through hierarchical feature learning yield acceptable success rates, they often require tremendous amounts of data when trained in a supervised manner. An unsupervised generative framework utilizing a variational autoencoder (VAE) is proposed in this work in order to create better disentangled representations for the downstream classification task. The disentanglement is further enforced using a hyperparameter $\beta $ . For the purpose of better segregating the spectro-temporal features, an intermediate non-linearly scaled time-frequency representation is also employed in conjunction with $\beta $ -VAE. Experimental analysis of various classifier configurations yields encouraging results in terms of data efficiency and classification accuracy on target records collected from various locations of the Indian Ocean.

中文翻译：

---

使用深度生成的被动声纳目标分类 $\beta $-VAE


与被动声纳数据相关的内在复杂性使得目标识别任务极具挑战性。基于手工设计的特征变换的传统分类器架构通常无法分解观察到的目标记录中的高维非线性结构。尽管通过分层特征学习的现代深度学习算法产生了可接受的成功率，但在以监督方式进行训练时，它们通常需要大量数据。这项工作提出了一种利用变分自动编码器（VAE）的无监督生成框架，以便为下游分类任务创建更好的解缠结表示。使用超参数 $\beta $ 进一步强制解开。为了更好地分离谱时特征，中间非线性缩放时频表示也与$\beta$-VAE结合使用。对各种分类器配置的实验分析在从印度洋不同地点收集的目标记录的数据效率和分类准确性方面产生了令人鼓舞的结果。