# Ensemble of Small Classifiers For Imbalanced White Blood Cell Classification

Source: [Ensemble of Small Classifiers For Imbalanced White Blood Cell Classification](<https://www.sota2.com/research/paper/69c21a6f0636e5bf4afc46fc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T05:00:04.214Z

Authors: Siddharth Srivastava, Adam Smith, Scott Brooks, Jack Bacon, Till Bretschneider

Published: 2026-03-21T15:24:52.000Z

## Abstract

Automating white blood cell classification for diagnosis of leukaemia is a promising alternative to time-consuming and resource-intensive examination of cells by expert pathologists. However, designing robust algorithms for classification of rare cell types remains challenging due to variations in staining, scanning and inter-patient heterogeneity. We propose a lightweight ensemble approach for classification of cells during Haematopoiesis, with a focus on the biology of Granulopoiesis, Monocytopoiesis and Lymphopoiesis. Through dataset expansion to alleviate some class imbalance, we demonstrate that a simple ensemble of lightweight pretrained SwinV2-Tiny, DinoBloom-Small and ConvNeXT-V2-Tiny models achieves excellent performance on this challenging dataset. We train 3 instantiations of each architecture in a stratified 3-fold cross-validation framework; for an input image, we forward-pass through all 9 models and aggregate through logit averaging. We further reason on the weaknesses of our model in confusing similar-looking myelocytes in granulopoiesis and lymphocytes in lymphopoiesis. Code: https://gitlab.com/siddharthsrivastava/wbc-bench-2026.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [White blood cell classification on WBCBench Out-of-Fold (train + eval)](<https://www.sota2.com/research/sota/white-blood-cell-classification-on-wbcbench-out-of-fold-train-plus-eval.md>): White Blood Cell classification; WBCBench Out-of-Fold (train + eval); Macro F1: 77.98.

- [White blood cell classification on WBCBench (test)](<https://www.sota2.com/research/sota/white-blood-cell-classification-on-wbcbench-test.md>): White Blood Cell classification; WBCBench (test); Macro F1: 67.72.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.20856>)

[PDF](<https://arxiv.org/pdf/2603.20856.pdf>)