Search Results for author:
Found 2 papers, 1 papers with code
Topology-Preserving Adversarial Training
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i. e., accuracy on natural samples has reduced significantly.
Progressive Domain Expansion Network for Single Domain Generalization
A series of strategies are introduced to guarantee the safety and effectiveness of the expanded domains.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
