aiqbench analysis
The paper introduces ONCship, a 4,521-hour underwater acoustic dataset built from hydrophone recordings and AIS vessel data, and benchmarks it on self-supervised representation learning, vessel-type classification, and vessel-identity classification. For ML readers, the useful signals are the scale gain over existing corpora like DeepShip and ShipsEar and the reported 62.45% linear-probe accuracy, though the benchmarks are single-paper results that need independent replication. The MMSI-level task, with 53% Top-1 accuracy, is an early feasibility result rather than a solved problem.
ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition
arXiv:2610.19722v1 Announce Type: cross Abstract: Recent advances in deep learning have significantly improved underwater acoustic vessel recognition. However, existing publicly available datasets are typically limited in scale, hindering large-scale representation learning and downstream task evaluation. To address this limitation, we introduce ONCship, a large-scale underwater acoustic dataset comprising 4521 hours of curated recordings from Ocean Networks Canada (ONC) hydrophones and Automatic Identification System (AIS) data. We evaluate the proposed dataset across three tasks: self-supervised representation learning, vessel-type classification, and MMSI-Level Vessel Classification. Experiments on DeepShip and ShipsEar demonstrate the effectiveness of ONCship for acoustic representation learning, with joint pre-training on ONCship and AudioSet achieving a classification accuracy of 62.45% on DeepShip through linear probing. Furthermore, incorporating ONCship as auxiliary training data improves downstream vessel-type classification performance. Beyond conventional vessel-type classification, we further investigate MMSI-Level Vessel Classification, treating each vessel as a distinct identity. Experimental results show that models fine-tuned with different loss functions achieve Top-1 accuracies exceeding 53% and Top-5 accuracies approaching 69%, demonstrating the feasibility of distinguishing individual vessels through MMSI-Level Vessel Classification. Overall, ONCship provides a valuable resource for underwater acoustic representation learning and vessel recognition, while its rich vessel-level metadata enables further exploration of MMSI-Level Vessel Classification.
Abstract:Recent advances in deep learning have significantly improved underwater acoustic vessel recognition. However, existing publicly available datasets are typically limited in scale, hindering large-scale representation learning and downstream task evaluation. To address this limitation, we introduce ONCship, a large-scale underwater acoustic dataset comprising 4521 hours of curated recordings from Ocean Networks Canada (ONC) hydrophones and Automatic Identification System (AIS) data. We evaluate the proposed dataset across three tasks: self-supervised representation learning, vessel-type classification, and MMSI-Level Vessel Classification. Experiments on DeepShip and ShipsEar demonstrate the effectiveness of ONCship for acoustic representation learning, with joint pre-training on ONCship and AudioSet achieving a classification accuracy of 62.45% on DeepShip through linear probing. Furthermore, incorporating ONCship as auxiliary training data improves downstream vessel-type classification performance. Beyond conventional vessel-type classification, we further investigate MMSI-Level Vessel Classification, treating each vessel as a distinct identity. Experimental results show that models fine-tuned with different loss functions achieve Top-1 accuracies exceeding 53% and Top-5 accuracies approaching 69%, demonstrating the feasibility of distinguishing individual vessels through MMSI-Level Vessel Classification. Overall, ONCship provides a valuable resource for underwater acoustic representation learning and vessel recognition, while its rich vessel-level metadata enables further exploration of MMSI-Level Vessel Classification.
Sound (cs.SD); Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
arXiv:2610.19722 [cs.SD]
(or arXiv:2610.19722v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2610.19722 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 294 words
Related coverage
Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddings
arXiv · Sep 23, 2026
The Open ASR Leaderboard Adds Its First Global South Language
Hugging Face · Aug 28, 2026
UA-Bench: Benchmarking Large Audio-Language Models on Underwater Acoustic Recognition
arXiv · Oct 15, 2026
Best Open Speech Recognition (ASR) Models in 2026: WER, Languages, Latency, and License Compared
MarkTechPost · Jul 23, 2026