Methods › General › Self-Supervised Learning › SwAV

Swapping Assignments between Views

SwAV

55 papers tagged archive 2025-07-28

Introduced by Mathilde Caron et al. in Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

SwaV, 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.

PaperSourceSee Code · facebookresearch/swav

Papers archive 2025-07-28

30 shown of 55, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 92 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Self-Supervised Learning18
Contrastive Learning8
Image Classification7
Representation Learning7
Clustering6
Survival Analysis5
Transfer Learning5
Object Detection4
Prognosis4
Semantic Segmentation4
object-detection4
Data Augmentation3
Diversity3
Reinforcement Learning3
Semi-Supervised Image Classification3
image-classification3
reinforcement-learning3
Epidemiology2
Federated Learning2
Knowledge Distillation2

Usage over time archive 2025-07-28

Papers per year tagged with SwAV: 2020 to 2025, peak 13 13 0 2020: 3 papers 2020 2021: 13 papers 2021 2022: 13 papers 2022 2023: 13 papers 2023 2024: 7 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (55 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Self-Supervised Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections