Self-Supervised Learning
Inpainting
Introduced by Pathak et al. in Context Encoders: Feature Learning by InpaintingTrain a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Source: Context Encoders: Feature Learning by InpaintingPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Inpainting | 200 | 23.15% |
| Image Generation | 55 | 6.37% |
| Denoising | 49 | 5.67% |
| Video Inpainting | 39 | 4.51% |
| Semantic Segmentation | 24 | 2.78% |
| Super-Resolution | 18 | 2.08% |
| Novel View Synthesis | 16 | 1.85% |
| Facial Inpainting | 15 | 1.74% |
| Image Restoration | 15 | 1.74% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
