Robust White Blood Cell Classification with Stain-Normalized Decoupled Learning and Ensembling
This work addresses robust classification for hematology applications, but it appears incremental as it builds on existing methods like decoupled learning and ensembling.
The paper tackled the problem of white blood cell classification under real-world variations like staining differences and class imbalance, achieving top rank on the WBCBench 2026 challenge leaderboard.
White blood cell (WBC) classification is fundamental for hematology applications such as infection assessment, leukemia screening, and treatment monitoring. However, real-world WBC datasets present substantial appearance variations caused by staining and scanning conditions, as well as severe class imbalance in which common cell types dominate while rare but clinically important categories are underrepresented. To address these challenges, we propose a stain-normalized, decoupled training framework that first learns transferable representations using instance-balanced sampling, and then rebalances the classifier with class-aware sampling and a hybrid loss combining effective-number weighting and focal modulation. In inference stage, we further enhance robustness by ensembling various trained backbones with test-time augmentation. Our approach achieved the top rank on the leaderboard of the WBCBench 2026: Robust White Blood Cell Classification Challenge at ISBI 2026.