# Target-Independent Domain Adaptation for WBC Classification using Generative Latent Search

arXiv: https://arxiv.org/abs/2005.05432 · HTML: https://mlsanity.com/paper/2005.05432/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2020.

## Built on by (most cited first, 6 of 6)

- [Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain](https://mlsanity.com/paper/2202.10725/) (2022)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting](https://mlsanity.com/paper/2304.00741/) (2023)
- [Selective Test-Time Adaptation for Unsupervised Anomaly Detection using Neural Implicit Representations](https://mlsanity.com/paper/2410.03306/) (2024)
- [Robust Framework for COVID-19 Identification from a Multicenter Dataset of Chest CT Scans](https://mlsanity.com/paper/2109.09241/) (2021)
- [Towards Real-world Lens Active Alignment with Unlabeled Data via Domain Adaptation](https://mlsanity.com/paper/2601.03718/) (2026)

## Abstract (arXiv)

Automating the classification of camera-obtained microscopic images of White Blood Cells (WBCs) and related cell subtypes has assumed importance since it aids the laborious manual process of review and diagnosis. Several State-Of-The-Art (SOTA) methods developed using Deep Convolutional Neural Networks suffer from the problem of domain shift - severe performance degradation when they are tested on data (target) obtained in a setting different from that of the training (source). The change in the target data might be caused by factors such as differences in camera/microscope types, lenses, lighting-conditions etc. This problem can potentially be solved using Unsupervised Domain Adaptation (UDA) techniques albeit standard algorithms presuppose the existence of a sufficient amount of unlabelled target data which is not always the case with medical images. In this paper, we propose a method for UDA that is devoid of the need for target data. Given a test image from the target data, we obtain its 'closest-clone' from the source data that is used as a proxy in the classifier. We prove the existence of such a clone given that infinite number of data points can be sampled from the source distribution. We propose a method in which a latent-variable generative model based on variational inference is used to simultaneously sample and find the 'closest-clone' from the source distribution through an optimization procedure in the latent space. We demonstrate the efficacy of the proposed method over several SOTA UDA methods for WBC classification on datasets captured using different imaging modalities under multiple settings.