most citedSCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training

1 citations · 1 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2023★ 1 cited

SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Training

Rui Xu, Wenkang Qin, Peixiang Huang +2

Deep Neural Networks (DNNs) are expected to provide explanation for users to understand their black-box predictions. Saliency map is a common form of explanation illustrating the h…

eess.IV2023

Assessing and Enhancing Robustness of Deep Learning Models with Corruption Emulation in Digital Pathology

Peixiang Huang, Songtao Zhang, Yulu Gan +6

Deep learning in digital pathology brings intelligence and automation as substantial enhancements to pathological analysis, the gold standard of clinical diagnosis. However, multip…