Self-Supervised Learning
ClusterFit
Introduced by Yan et al. in ClusterFit: Improving Generalization of Visual RepresentationsClusterFit is a self-supervision approach for learning image representations. Given a dataset, we (a) cluster its features extracted from a pre-trained network using k-means and (b) re-train a new network from scratch on this dataset using cluster assignments as pseudo-labels.
Source: ClusterFit: Improving Generalization of Visual Representations
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Action Classification | 1 | 33.33% |
| Clustering | 1 | 33.33% |
| Image Classification | 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 |
