发表机构
Kitware, Inc.（Kitware公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对水下声学目标识别中数据泄漏导致性能虚高的问题，提出UniqueShip基准数据集，通过严格控制划分，证明船舶多样性比总时长更重要，并提供基线与分析。
AI 中文摘要
水下声学目标识别（UATR）非常适合机器学习，但其进展受到缺乏大规模、多样化且公开可用的标注数据集的阻碍。在这项工作中，我们引入了UniqueShip，一个面向UATR应用的机器学习就绪基准数据集，其数据来源于开放的加拿大海洋网络（ONC）存储库。与以往数据集不同，我们明确控制了训练集和评估集之间的“数据泄漏”，以确保更可靠和可泛化的模型评估，避免鼓励模型记忆个别船舶。我们证明，在两个著名的UATR数据集中，典型的随机数据划分会导致虚假乐观的测试性能，与我们的更仔细划分相比，准确率提高了10-48个百分点。在UniqueShip上的消融实验进一步表明，将独特船舶数量加倍可使准确率提高2.4-2.6个百分点，而将总音频时长加倍仅提高0.8-1.3个百分点，这表明船舶多样性应比总时长更多地驱动数据集策展。我们提供了基于卷积和Transformer骨干网络的基线，并分析了船舶元数据与分类性能的相关性，发现个体船舶特征对分类难度的预测远优于仅使用到水听器的距离。总体而言，UniqueShip包含来自4,218艘独特船舶的2,460小时船舶辐射音频（包括背景共3,437小时）。我们在该HTTP URL上发布了数据集、代码和易于下载的划分，以促进进一步的UATR研究。
英文摘要
Underwater Acoustic Target Recognition (UATR) of ships is well-suited for machine learning, yet its progress is hindered by the lack of large, diverse, and publicly available labeled datasets. In this work, we introduce UniqueShip, a machine learning-ready benchmark dataset for UATR applications sourced from the open Ocean Networks Canada (ONC) repository. Unlike previous datasets, we explicitly control for "data leakage" between the training and evaluation sets to ensure more reliable and generalizable model evaluation that does not encourage the model to memorize individual ships. We demonstrate that typical, random data partitioning in two prominent UATR datasets leads to falsely optimistic test performance, increasing accuracy by 10-48 percentage points compared to our more careful partitioning. Ablations on UniqueShip further show that doubling the number of unique vessels improves accuracy by 2.4-2.6 percentage points, while doubling total audio duration improves only by 0.8-1.3 points, indicating that vessel diversity should drive dataset curation more than total hours. We provide baselines with convolutional and transformer backbones, and analyze how ship metadata correlates with classification performance, finding that individual vessel characteristics predict classification difficulty far better than distance to the hydrophone alone. Overall, UniqueShip contains 2,460 hours of ship-radiated audio from 4,218 unique vessels (3,437 hours including background). We publish the dataset, code, and easy-to-download splits at uniqueshipdata.org to foster further UATR research.
Comments9 pages paper, 4 pages supplementary at the end, accepted/will be published at Oceans 2026. Note that while this is underwater acoustics, we process it using computer vision models and methods (i.e. spectrograms)
