Image Data Augmentation
CutMix
Introduced by Yun et al. in CutMix: Regularization Strategy to Train Strong Classifiers with Localizable FeaturesCutMix is an image data augmentation strategy. Instead of simply removing pixels as in Cutout, we replace the removed regions with a patch from another image. The ground truth labels are also mixed proportionally to the number of pixels of combined images. The added patches further enhance localization ability by requiring the model to identify the object from a partial view.
Source: CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 56 | 20.51% |
| Image Classification | 21 | 7.69% |
| Semantic Segmentation | 19 | 6.96% |
| Instance Segmentation | 7 | 2.56% |
| Real-Time Object Detection | 7 | 2.56% |
| General Classification | 7 | 2.56% |
| Classification | 6 | 2.20% |
| Semi-Supervised Semantic Segmentation | 6 | 2.20% |
| Autonomous Driving | 5 | 1.83% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
