A Gradual Adversarial Training Method for Semantic Segmentation
Deep neural networks (DNNs) have achieved great success in various computer vision tasks. However, they are susceptible to artificially designed adversarial perturbations, which limit their deployment in security-critical applications. In this paper, we propose a gradual adversarial training (GAT) m...
Sparad:
| Huvudupphov: | , , |
|---|---|
| Materialtyp: | Artigo |
| Språk: | Inglês |
| Utgiven: |
MDPI AG
2024-11-01
|
| Serie: | Remote Sensing |
| Ämnen: | |
| Länkar: | https://www.mdpi.com/2072-4292/16/22/4277 |
| Taggar: |
Inga taggar, Lägg till första taggen!
|