# A Hierarchical Ensemble Inference Pipeline for Robust White Blood Cell Classification Under Domain Shifts

arXiv: https://arxiv.org/abs/2604.23271 · HTML: https://mlsanity.com/paper/2604.23271/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology](https://mlsanity.com/paper/2404.05022/) (2024)
- [Histogram of Cell Types: Deep Learning for Automated Bone Marrow Cytology](https://mlsanity.com/paper/2107.02293/) (2021)
- [WBCBench 2026: A Challenge for Robust White Blood Cell Classification Under Class Imbalance](https://mlsanity.com/paper/2604.10797/) (2026)
- [Classification of All Blood Cell Images using ML and DL Models](https://mlsanity.com/paper/2308.06300/) (2023)

## Built on by (most cited first, 1 of 1)

- [Retrieval-Augmented Vision Foundation Models for Robust Leukemia Cell Classification across Multiple Microscopy Datasets](https://mlsanity.com/paper/2608.10657/) (2026)

## Abstract (arXiv)

Automated white blood cell (WBC) classification is essential for scalable leukaemia screening. However, real-world deployment is challenged by domain shifts caused by staining protocols, scanner characteristics, and inter-laboratory variability, which often degrade model performance. The White Blood Cell Classification Challenge (WBCBench) at ISBI 2026 aims to advance robust WBC recognition, with a focus on accurately identifying blast cells and other clinically critical rare subtypes. We propose a memory-augmented, hierarchical ensemble pipeline for WBC classification under domain shifts, leveraging a feature bank and a DinoBloom backbone fine-tuned with LoRA. Our three-stage inference hierarchy combines k-nearest neighbors (kNN) retrieval at each level, reducing over-reliance on any single decision. Evaluated on the WBCBench dataset, our method ranks within the top ten by macro F1-score in the final testing phase.