Adversarial Training
DropAttack
Introduced by Ni et al. in DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural NetworksDropAttack is an adversarial training method that adds intentionally worst-case adversarial perturbations to both the input and hidden layers in different dimensions and minimizes the adversarial risks generated by each layer.
Source: DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
