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 | 193 | 21.96% |
| Image Generation | 55 | 6.26% |
| Denoising | 52 | 5.92% |
| Video Inpainting | 40 | 4.55% |
| Semantic Segmentation | 23 | 2.62% |
| Decoder | 23 | 2.62% |
| Novel View Synthesis | 17 | 1.93% |
| Super-Resolution | 17 | 1.93% |
| Image Restoration | 16 | 1.82% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
