Regularization
Auxiliary Batch Normalization
Introduced by Xie et al. in Adversarial Examples Improve Image RecognitionAuxiliary Batch Normalization is a type of regularization used in adversarial training schemes. The idea is that adversarial examples should have a separate batch normalization components to the clean examples, as they have different underlying statistics.
Source: Adversarial Examples Improve Image Recognition
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Domain Generalization | 3 | 13.04% |
| Image Classification | 2 | 8.70% |
| Meta-Learning | 1 | 4.35% |
| Speaker Verification | 1 | 4.35% |
| Voice Conversion | 1 | 4.35% |
| Diversity | 1 | 4.35% |
| Domain Adaptation | 1 | 4.35% |
| Image Generation | 1 | 4.35% |
| Text to Image Generation | 1 | 4.35% |
Batch Normalization
