arXiv cs.AI· Taqi Hamoda, Hayat Rajani, Nuno Gracias·· 12 小时前AI 评分18
BenthicDINO：面向视角不变侧扫声呐表征的物理引导自蒸馏框架
BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations
AI 导读
BenthicDINO 是一个物理引导的自监督学习框架，用 ConvNeXt-v2 骨干、物理引导增强和 HSIC 惩罚，显式约束特征对斜距、入射角等观测参数的不变性，从而把采集几何与海底反射率解耦。在海底栖息地制图中仅用 10% 标签即接近峰值性能，并在 AI4Shipwrecks 基准上以冻结表征超越全监督基线。
正文 · 原文
Abstract:Automated interpretation of side-scan sonar (SSS) imagery is traditionally hindered by view-dependence, as recorded intensities inextricably conflate intrinsic seabed reflectivity with transient acquisition geometries and acoustic artifacts. To address this, we introduce BenthicDINO, a physics-informed self-supervised learning framework that decouples acquisition dynamics from seabed representations. Utilizing a ConvNeXt-v2 backbone, physics-guided augmentations, and an HSIC penalty, BenthicDINO explicitly enforces feature invariance to physical viewing parameters like slant range and incidence angle. Evaluations demonstrate exceptional data efficiency - achieving near-peak performance in benthic habitat mapping with only 10% of available labels - and strong cross-domain generalization, outperforming fully supervised baselines on the AI4Shipwrecks benchmark using frozen representations.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2608.23215 [cs.CV] |
| (or arXiv:2608.23215v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2608.23215 arXiv-issued DOI via DataCite |
Submission history
From: Taqi Hamoda [view email]
[v1]
Mon, 24 Aug 2026 13:11:22 UTC (7,095 KB)
[v2]
Fri, 16 Oct 2026 14:33:36 UTC (8,965 KB)
来源：arXiv cs.AI · arxiv.org