Auxiliary 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 RecognitionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Domain Generalization | 3 | 16.67% |
Image Classification | 2 | 11.11% |
Domain Adaptation | 1 | 5.56% |
Image Generation | 1 | 5.56% |
Text-to-Image Generation | 1 | 5.56% |
Object Recognition | 1 | 5.56% |
Feature Importance | 1 | 5.56% |
Object Detection | 1 | 5.56% |
Adversarial Attack | 1 | 5.56% |