Image Data Augmentation
Object Dropout
Introduced by Jain et al. in Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image CaptioningObject Dropout is a technique that perturbs object features in an image for noisy student training. It performs at par with standard data augmentation techniques while being significantly faster than the latter to implement.
Source: Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Augmentation | 1 | 33.33% |
| Image Captioning | 1 | 33.33% |
| Semi Supervised Learning for Image Captioning | 1 | 33.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
