Self-Supervised Learning
Swapping Assignments between Views
Introduced by Caron et al. in Unsupervised Learning of Visual Features by Contrasting Cluster AssignmentsSwaV, or Swapping Assignments Between Views, is a self-supervised learning approach that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, it simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or views) of the same image, instead of comparing features directly as in contrastive learning. Simply put, SwaV uses a swapped prediction mechanism where we predict the cluster assignment of a view from the representation of another view.
Source: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Self-Supervised Learning | 17 | 13.71% |
| Image Classification | 7 | 5.65% |
| Clustering | 6 | 4.84% |
| Prognosis | 4 | 3.23% |
| Object Detection | 4 | 3.23% |
| Semantic Segmentation | 4 | 3.23% |
| Survival Analysis | 3 | 2.42% |
| Reinforcement Learning | 3 | 2.42% |
| Diversity | 3 | 2.42% |
LARS
