Self-supervised feature learning for rapid processing of marine imagery

用于快速处理海洋图像的自监督特征学习

• 批准号: LP220200949
• 负责人: Prof Stefan Williams
• 金额: $ 33.33万
• 依托单位: The University of Sydney
• 依托单位国家: 澳大利亚
• 项目类别: Linkage Projects
• 财政年份: 2023
• 资助国家: 澳大利亚
• 起止时间: 2023-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/LP220200949
• 关键词: Self; supervised; feature; learning; rapid

Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques that use large amounts of unlabeled data to enhance performance. Our design takes advantage of additional information available for marine imagery such as geolocation and remote sensing context. We will explore how these representations can guide additional sampling and improve performance in classification tasks.

科学研究、保护区的设计和管理以及海洋工业活动的法规遵从性都需要对海洋环境健康的快速和可靠的定量估计。澳大利亚正在以越来越快的速度收集海底图像，但专家注释跟不上，这意味着典型的机器学习方法难以实现。该项目将开发使用大量未标记数据来提高性能的自我监督技术。我们的设计利用了可用于海洋图像的其他信息，如地理位置和遥感背景。我们将探索这些表示如何指导额外的采样并提高分类任务的性能。