WaveFuse-AL: Cyclical and Performance-Adaptive Multi-Strategy Active Learning for Medical Images

TL;DR

WaveFuse-AL introduces a dynamic multi-strategy active learning framework that adaptively combines multiple acquisition strategies with cyclical and performance-based adjustments, significantly improving annotation efficiency in medical imaging tasks.

Contribution

It presents a novel adaptive fusion framework for active learning that dynamically adjusts strategy importance using cyclical and performance cues, outperforming existing methods.

Findings

Consistently outperforms single and alternating strategies across benchmarks.

Achieves statistically significant improvements in 10 out of 12 metrics.

Maximizes utility of limited annotation budgets.

Abstract

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.