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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thakur, Nishchala, Kochhar, Swati, Bathula, Deepti R., Gupta, Sukrit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915626682941440
author Thakur, Nishchala
Kochhar, Swati
Bathula, Deepti R.
Gupta, Sukrit
author_facet Thakur, Nishchala
Kochhar, Swati
Bathula, Deepti R.
Gupta, Sukrit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15132
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WaveFuse-AL: Cyclical and Performance-Adaptive Multi-Strategy Active Learning for Medical Images
Thakur, Nishchala
Kochhar, Swati
Bathula, Deepti R.
Gupta, Sukrit
Computer Vision and Pattern Recognition
Machine Learning
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.
title WaveFuse-AL: Cyclical and Performance-Adaptive Multi-Strategy Active Learning for Medical Images
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2511.15132