WaveFuse-AL: Cyclical and Performance-Adaptive Multi-Strategy Active Learning for Medical Images
This work addresses annotation cost reduction in medical imaging, offering an incremental improvement by dynamically combining existing strategies.
The paper tackled the problem of inconsistent behavior in active learning strategies for medical imaging by proposing WaveFuse-AL, a framework that adaptively fuses multiple acquisition strategies, resulting in statistically significant performance improvements on ten out of twelve metric measurements across three benchmarks.
Active learning reduces annotation costs in medical imaging by strategically selecting the most informative samples for labeling. However, individual acquisition strategies often exhibit inconsistent behavior across different stages of the active learning cycle. We propose Cyclical and Performance-Adaptive Multi-Strategy Active Learning (WaveFuse-AL), a novel framework that adaptively fuses multiple established acquisition strategies-BALD, BADGE, Entropy, and CoreSet throughout the learning process. WaveFuse-AL integrates cyclical (sinusoidal) temporal priors with performance-driven adaptation to dynamically adjust strategy importance over time. We evaluate WaveFuse-AL on three medical imaging benchmarks: APTOS-2019 (multi-class classification), RSNA Pneumonia Detection (binary classification), and ISIC-2018 (skin lesion segmentation). Experimental results demonstrate that WaveFuse-AL consistently outperforms both single-strategy and alternating-strategy baselines, achieving statistically significant performance improvements (on ten out of twelve metric measurements) while maximizing the utility of limited annotation budgets.