查询策略基准测试：迈向未来的深度主动学习
Benchmarking of Query Strategies: Towards Future Deep Active Learning
AI总结：
本文构建深度主动学习查询策略的标准化基准，在含医学与视觉检测图像的六个数据集上评估多种策略，并验证基于完全训练模型的DAL方法效果。
摘要：
在本研究中，我们对深度主动学习（DAL）的查询策略进行基准测试。DAL通过仅标注由查询策略选出的高质量样本来降低标注成本。现有研究存在两个主要问题：实验设置不标准，导致难以评估现有方法；且大多数实验是在CIFAR或MNIST数据集上进行的。因此，我们为DAL制定了标准化实验设置，并使用六个数据集（包括包含医学和视觉检测图像的数据集）研究各种查询策略的有效性。此外，由于当前大多数DAL方法基于模型，我们使用经过完全训练的模型进行查询来开展验证实验，以研究这些方法在六个数据集上的有效性。我们的代码可在https://github.com/ia-gu/Benchmarking-of-Query-Strategies-Towards-Future-Deep-Active-Learning获取。
英文摘要：
In this study, we benchmark query strategies for deep actice learning~(DAL). DAL reduces annotation costs by annotating only high-quality samples selected by query strategies. Existing research has two main problems, that the experimental settings are not standardized, making the evaluation of existing methods is difficult, and that most of experiments were conducted on the CIFAR or MNIST datasets. Therefore, we develop standardized experimental settings for DAL and investigate the effectiveness of various query strategies using six datasets, including those that contain medical and visual inspection images. In addition, since most current DAL approaches are model-based, we perform verification experiments using fully-trained models for querying to investigate the effectiveness of these approaches for the six datasets. Our code is available at \href{https://github.com/ia-gu/Benchmarking-of-Query-Strategies-Towards-Future-Deep-Active-Learning}
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
