Class-Balancing Deep Active Learning with Auto-Feature Mixing and Minority Push-Pull Sampling

Deep neural networks demand large-scale labeled dataset for optimal performance, yet the cost of annotation remains high. Deep active learning (DAL) offers a promising approach to reduce annotation cost while maintaining performance. However, traditional DAL methods often fail to balance performance and computational efficiency, and overlook the challenge posed by class imbalance. To address these challenges, we propose a novel framework, named Class-Balancing Deep Active Learning(CB-DAL), comprising two key modules: auto-mode feature mixing (Auto-FM) and minority push-pull sampling (MPPS). Auto-FM identifies informative samples by simply detecting in inconsistencies in predicted labels after feature mixing, while MPPS mitigates the class imbalance within the selected training pool by selecting candidates whose features close to the minority class centroid while distant from features of the labelled majority class. Evaluated across varying class imbalance ratios and dataset scales, CB-DAL outperforms traditional DAL methods and the counterparts designed for imbalanced dataset. Our method provides a simple yet effective solution to the class imbalance problem in DAL, with broad potential applications.