利用现有稀疏点标注进行底栖图像的密集分割
Leveraging existing sparse point annotations for benthic imagery dense segmentation
- Universidad de Zaragoza（萨拉戈萨大学）
- Berklee College of Music（伯克利音乐学院）
- University of Washington（华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究结合SAM2基础模型与底栖图像的稀疏专家点标注，提出自动筛选可靠点的机制以生成高质量伪真值掩码，训练细粒度分割模型，还引入新基准推进生态分析。
AI中文摘要：
海洋生态系统的健康状况是全球环境变化的关键指标，但水下观测的物理限制以及处理海洋图像的固有挑战严重制约了系统监测的可扩展性。尽管最近的视觉基础模型（如Segment Anything Model（SAM）系列）展现出巨大潜力，但它们在这些复杂场景中所需的细粒度识别方面仍存在不足，且仍需要专家监督。本研究通过将最先进的基础模型与现有稀疏监督相结合来解决这一差距。由于历史底栖调查通常仅在每张图像上标注少量稀疏的专家点，我们将这些遗留的点标签作为视觉提示用于SAM2。我们的主要贡献是一种新颖的机制，用于自动识别这些点中哪些适合用于传播，哪些会产生负面影响。通过过滤不可靠的点，我们提取出高质量的伪真值掩码，能够用于训练更准确、细粒度的语义分割模型。我们在公开的底栖数据上验证了该方法的有效性，并引入了一个包含真实世界稀疏专家标注的新的、具有挑战性的基准，为可扩展的生态分析铺平了道路。
英文摘要：
The health of marine ecosystems is a critical indicator of global environmental change, yet the physical constraints of underwater observation and the intrinsic challenges of processing marine imagery severely limit the scalability of systematic monitoring. While recent visual foundation models such as the Segment Anything Model (SAM) series show great promise, they still struggle with the fine-grained recognition required in these complex scenarios and still require expert supervision. Our work addresses this gap by bridging state-of-the-art foundation models with existing sparse supervision. Because historical benthic surveys are typically annotated with only a few sparse expert points per image, we utilize these legacy point-labels as visual prompts for SAM2. Our primary contribution is a novel mechanism to automatically identify which of these points are suitable, and which are actively harmful, when used for propagation. By filtering out unreliable points, we extract high-quality pseudo-ground-truth masks capable of training more accurate, fine-grained semantic segmentation models. We demonstrate the effectiveness of our approach on public benthic data and introduce a new, challenging benchmark featuring real-world sparse expert annotations, paving the way for scalable ecological analysis.
