Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessment
This work improves active learning efficiency for semantic segmentation, reducing training burden, but it is incremental as it builds on existing methods with novel enhancements.
The paper tackles the challenge of active learning for semantic segmentation by addressing class imbalance and ambiguous sample definitions, resulting in a method that outperforms state-of-the-art approaches on Cityscapes and PASCAL VOC datasets.
Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and different ways of defining "sample" (pixels, areas, etc.), leaving the interpretation of the data distribution ambiguous. We propose "Maturity-Aware Distribution Breakdown-based Active Learning'' (MADBAL), an AL method that benefits from a hierarchical approach to define a multiview data distribution, which takes into account the different "sample" definitions jointly, hence able to select the most impactful segmentation pixels with comprehensive understanding. MADBAL also features a novel uncertainty formulation, where AL supporting modules are included to sense the features' maturity whose weighted influence continuously contributes to the uncertainty detection. In this way, MADBAL makes significant performance leaps even in the early AL stage, hence reducing the training burden significantly. It outperforms state-of-the-art methods on Cityscapes and PASCAL VOC datasets as verified in our extensive experiments.