Automatic Training Data Search and Model Evaluation by Measuring Domain Gap

通过测量域差距自动训练数据搜索和模型评估

• 批准号: DP210102801
• 负责人: Prof Tamás (Tom) Gedeon
• 金额: $ 35.65万
• 依托单位: The Australian National University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2021
• 资助国家: 澳大利亚
• 起止时间: 2021-12-11 至 2024-12-10
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP210102801
• 关键词: Automatic; Training; Data; Search; Model

We aim to investigate computer vision training data and test data, using automatically generated data sets for facial expression recognition and object re-identification. This project expects to quantify and understand the domain gap, the distribution difference between training and test data sets. Expected outcomes of this project are insights on measuring the domain gap, the ability to estimate model performance without accessing expensive test labels and improvements to system generalisation. This should provide significant benefits for computer vision applications that currently require expensive labelling, and commercial and economic benefits across sectors such as transportation, security and manufacturing.

我们的目标是研究计算机视觉训练数据和测试数据，使用自动生成的数据集进行面部表情识别和物体再识别。这个项目期望量化和理解领域差距，训练和测试数据集之间的分布差异。这个项目的预期结果是对测量领域差距的洞察，在不访问昂贵的测试标签和改进系统泛化的情况下估计模型性能的能力。这将为目前需要昂贵标签的计算机视觉应用以及运输，安全和制造等部门的商业和经济效益提供显着的好处。