Confident Coreset for Active Learning in Medical Image Analysis
This work addresses the challenge of expensive and time-consuming annotation in medical data, offering a solution for improving deep learning model training with limited labeled data, though it appears incremental as it builds on existing active learning approaches.
The paper tackles the problem of limited annotation budgets in medical image analysis by proposing a novel active learning method called confident coreset, which selects informative samples based on both uncertainty and distribution, and demonstrates superior performance over other methods in comparative experiments on two medical image analysis tasks.
Recent advances in deep learning have resulted in great successes in various applications. Although semi-supervised or unsupervised learning methods have been widely investigated, the performance of deep neural networks highly depends on the annotated data. The problem is that the budget for annotation is usually limited due to the annotation time and expensive annotation cost in medical data. Active learning is one of the solutions to this problem where an active learner is designed to indicate which samples need to be annotated to effectively train a target model. In this paper, we propose a novel active learning method, confident coreset, which considers both uncertainty and distribution for effectively selecting informative samples. By comparative experiments on two medical image analysis tasks, we show that our method outperforms other active learning methods.