Self-Supervised Learning
Jigsaw
Introduced by Noroozi et al. in Unsupervised Learning of Visual Representations by Solving Jigsaw PuzzlesJigsaw is a self-supervision approach that relies on jigsaw-like puzzles as the pretext task in order to learn image representations.
Source: Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Self-Supervised Learning | 17 | 15.89% |
| General Classification | 8 | 7.48% |
| Semantic Segmentation | 6 | 5.61% |
| Image Classification | 4 | 3.74% |
| Object Detection | 4 | 3.74% |
| Domain Generalization | 4 | 3.74% |
| Unsupervised Representation Learning | 3 | 2.80% |
| Domain Adaptation | 3 | 2.80% |
| Object Recognition | 3 | 2.80% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |