Image Data Augmentation
CutBlur
Introduced by Yoo et al. in Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New StrategyCutBlur is a data augmentation method that is specifically designed for the low-level vision tasks. It cuts a low-resolution patch and pastes it to the corresponding high-resolution image region and vice versa. The key intuition of Cutblur is to enable a model to learn not only "how" but also "where" to super-resolve an image. By doing so, the model can understand "how much" instead of blindly learning to apply super-resolution to every given pixel.
Source: Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Denoising | 1 | 25.00% |
| Image Restoration | 1 | 25.00% |
| Image Super-Resolution | 1 | 25.00% |
| Super-Resolution | 1 | 25.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
