Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology 事件

Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology arXiv:2503.10629v2 Announce Type: replace Abstract: Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well studied in natural images, its application to biomedical and microscopy data remains limited. Existing self-supervised adversarial training methods overlook the hierarchical st