发表机构
University of Shanghai for Science and Technology; University of Science and Technology Liaoning; The Australian National University; Fujian University of Technology（上海理工大学; 辽宁科技大学; 澳大利亚国立大学; 福建理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对海事船舶检测的尾迹依赖问题，本文提出HullWake框架，分离船体与尾迹线索并通过多种策略抑制尾迹主导预测，在Curated-Wake数据集上实现多项性能提升。
AI 中文摘要
海事船舶检测器常面临船体尺寸小、对比度低或模糊，而尾迹更长且更易检测的场景，这产生了尾迹依赖问题：检测器可能漏检尾迹微弱的慢速或静止船舶，或在类尾迹的水体杂波上产生误检。本文提出HullWake，一种面向鲁棒海事船舶检测的先船体后尾迹框架。HullWake将以候选区域为中心的船体证据与定向尾迹上下文分离，通过双向候选区域锚定走廊提取尾迹线索，并通过尾迹响应监督、尾迹衰减一致性、仅尾迹置信度抑制及船体-尾迹去相关来抑制尾迹主导的预测。本文还引入了面向尾迹的评估协议，涵盖弱尾迹/无尾迹船舶、类尾迹难负样本、最差组平均精度（AP）及尾迹衰减后的置信度下降。实验在Curated-Wake数据集上开展，该数据集是约10000张图像的面向尾迹的海事数据集，由《航拍图像中的船舶》、SMD基准及SeaDronesSee整理而来，新增了检测级和分割级尾迹标注。与仅用边界框的检测器及掩码监督分割基线相比，HullWake在整体AP、弱/无尾迹鲁棒性、类尾迹误检、最差组AP及尾迹衰减后的置信度稳定性上均有提升。
英文摘要
Maritime vessel detectors often face scenes where hulls are small, low-contrast, or blurred, while wakes are longer and easier to detect. This creates a wake-reliance problem: detectors may miss slow or stationary vessels with weak wakes, or produce false positives on wake-like water clutter. We propose HullWake, a hull-first wake-second framework for robust maritime vessel detection. HullWake separates proposal-centered hull evidence from directional wake context, extracts wake cues with bidirectional proposal-anchored corridors, and suppresses wake-dominant predictions through wake response supervision, wake-attenuated consistency, wake-only confidence suppression, and hull--wake decorrelation. We also introduce a wake-oriented evaluation protocol covering weak/no-wake vessels, wake-like hard negatives, worst-group AP, and confidence drop after wake attenuation. Experiments are conducted on Curated-Wake, a wake-oriented maritime dataset of about 10,000 images curated from Ships/Vessels in Aerial Images, the SMD benchmark, and SeaDronesSee, with newly added detection- and segmentation-level wake annotations. Compared with box-only detectors and mask-supervised segmentation baselines, HullWake improves overall AP, weak/no-wake robustness, wake-like false positives, worst-group AP, and confidence stability after wake attenuation.
CommentsAccepted by ICIG 2026 (The 14th International Conference on Image and Graphics)
