Benchmarking of Query Strategies: Towards Future Deep Active Learning
This work addresses the lack of standardized evaluation in deep active learning, which is incremental but provides a foundation for future research.
The study benchmarks query strategies for deep active learning to reduce annotation costs, developing standardized experimental settings and testing on six datasets including medical and visual inspection images, with code made available.
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}