Machine learning and neural networks are now ubiquitous in sonar perception, but it lags behind the computer vision field due to the lack of data and pre-trained models specifically for sonar images. In this paper we present the Marine Debris Turntable dataset and produce pre-trained neural networks trained on this dataset, meant to fill the gap of missing pre-trained models for sonar images. We train Resnet 20, MobileNets, DenseNet121, SqueezeNet, MiniXception, and an Autoencoder, over several input image sizes, from 32 x 32 to 96 x 96, on the Marine Debris turntable dataset. We evaluate these models using transfer learning for low-shot classification in the Marine Debris Watertank and another dataset captured using a Gemini 720i sonar. Our results show that in both datasets the pre-trained models produce good features that allow good classification accuracy with low samples (10-30 samples per class). The Gemini dataset validates that the features transfer to other kinds of sonar sensors. We expect that the community benefits from the public release of our pre-trained models and the turntable dataset.

中文翻译：

---

声纳图像的预训练模型

机器学习和神经网络现在在声纳感知中无处不在，但由于缺乏数据和专门用于声纳图像的预训练模型，它落后于计算机视觉领域。在本文中，我们展示了 Marine Debris Turntable 数据集并生成在该数据集上训练的预训练神经网络，旨在填补声纳图像预训练模型缺失的空白。我们在 Marine Debris 转盘数据集上训练 Resnet 20、MobileNets、DenseNet121、SqueezeNet、MiniXception 和 Autoencoder，输入图像大小从 32 x 32 到 96 x 96。我们使用迁移学习对海洋垃圾水箱中的低炮分类和使用 Gemini 720i 声纳捕获的另一个数据集进行评估。我们的结果表明，在这两个数据集中，预训练模型产生了良好的特征，可以在低样本（每类 10-30 个样本）的情况下实现良好的分类精度。Gemini 数据集验证了特征转移到其他类型的声纳传感器。我们希望社区从我们的预训练模型和转盘数据集的公开发布中受益。