Adversarial Image Data Augmentation
MaxUp
Introduced by Gong et al. in MaxUp: A Simple Way to Improve Generalization of Neural Network TrainingMaxUp is an adversarial data augmentation technique for improving the generalization performance of machine learning models. The idea is to generate a set of augmented data with some random perturbations or transforms, and minimize the maximum, or worst case loss over the augmented data. By doing so, we implicitly introduce a smoothness or robustness regularization against the random perturbations, and hence improve the generation performance. For example, in the case of Gaussian perturbation, MaxUp is asymptotically equivalent to using the gradient norm of the loss as a penalty to encourage smoothness.
Source: MaxUp: A Simple Way to Improve Generalization of Neural Network Training
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 2 | 33.33% |
| Language Modelling | 2 | 33.33% |
| Few-Shot Image Classification | 1 | 16.67% |
| General Classification | 1 | 16.67% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
