most citedImproving Generalization of Adversarial Training via Robust Critical Fine-Tuning

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

collaborators

2 papers

cs.CV2024

Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning

Woo-Jin Ahn, Geun-Yeong Yang, Hyun-Duck Choi +1

Deep learning models for semantic segmentation often experience performance degradation when deployed to unseen target domains unidentified during the training phase. This is mainl…

cs.LG2023★ 2 cited

Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning

Kaijie Zhu, Jindong Wang, Xixu Hu +2

Deep neural networks are susceptible to adversarial examples, posing a significant security risk in critical applications. Adversarial Training (AT) is a well-established technique…