AdvDINO: Domain-Adversarial Self-Supervised Representation Learning for Spatial Proteomics

arXiv:2508.04955v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has emerged as a powerful approach for learning visual representations without manual annotations. However, the robustness of standard SSL methods to domain shift -- systematic differences across data sources -- remains uncertain, posing an especially critical challenge in biomedical imaging where batch effects can obscure true biological signals. We present AdvDINO, a domain-adversarial SSL framework that i