Image Data Augmentation
Random Mix-up
Introduced by Luu et al. in Expeditious Saliency-guided Mix-up through Random Gradient ThresholdingR-Mix (Random Mix-up) is a Mix-up family Data Augmentation method. It combines random Mix-up with Saliency-guided mix-up, producing a procedure that is fast and performant, while reserving good characteristics of Saliency-guided Mix-up such as low Expected Calibration Error and high Weakly-supervised Object Localization accuracy.
Source: Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Classifier calibration | 1 | 25.00% |
| Image Classification | 1 | 25.00% |
| Object Localization | 1 | 25.00% |
| Weakly-Supervised Object Localization | 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 |
