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 | 198 | 23.05% |
| Image Generation | 55 | 6.40% |
| Denoising | 50 | 5.82% |
| Video Inpainting | 40 | 4.66% |
| Semantic Segmentation | 23 | 2.68% |
| Super-Resolution | 18 | 2.10% |
| Novel View Synthesis | 16 | 1.86% |
| Facial Inpainting | 16 | 1.86% |
| Image Restoration | 15 | 1.75% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
