Normalization
Gradient Normalization
Introduced by Wu et al. in Gradient Normalization for Generative Adversarial NetworksGradient Normalization is a normalization method for Generative Adversarial Networks to tackle the training instability of generative adversarial networks caused by the sharp gradient space. Unlike existing work such as gradient penalty and spectral normalization, the proposed GN only imposes a hard 1-Lipschitz constraint on the discriminator function, which increases the capacity of the network.
Source: Gradient Normalization for Generative Adversarial Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Multi-Task Learning | 1 | 14.29% |
| Visual Localization | 1 | 14.29% |
| Domain Adaptation | 1 | 14.29% |
| Test-time Adaptation | 1 | 14.29% |
| MRI Reconstruction | 1 | 14.29% |
| Image Generation | 1 | 14.29% |
| Image Classification | 1 | 14.29% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
