Bridging Generalization Gaps in High Content Imaging Through Online Self-Supervised Domain Adaptation

• DOI: 10.48550/arxiv.2311.12623
• Publication Date: 2023-01-01
• Authors: Johan Fredin Haslum; C. Matsoukas; Karl‐Johan Leucho...; Kevin Smith
• Keywords: Extractor; Domain Adaptation; Coda

High Content Imaging (HCI) plays a vital role in modern drug discovery and development pipelines, facilitating various stages from hit identification to candidate characterization. Applying machine learning models these datasets can prove challenging as they typically consist of multiple batches, affected by experimental variation, especially if different imaging equipment have been used. Moreover, new data arrive, it is preferable that are analyzed an online fashion. To overcome this, we propose CODA, self-supervised domain adaptation approach. CODA divides the classifier's into generic feature extractor task-specific model. We adapt extractor's weights using cross-batch self-supervision while keeping model unchanged. Our results demonstrate this strategy significantly reduces generalization gap, achieving up 300% improvement when applied labs utilizing microscopes. be new, unlabeled out-of-domain sources sizes, single plate batches.