Methods › General › Clustering › SCAN-clustering
Semantic Clustering by Adopting Nearest Neighbours
SCAN-clustering
Introduced by Wouter Van Gansbeke et al. in SCAN: Learning to Classify Images without Labels
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SCAN automatically groups images into semantically meaningful clusters when ground-truth annotations are absent. SCAN is a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task is employed to obtain semantically meaningful features. Second, the obtained features are used as a prior in a learnable clustering approach.
Image source: Gansbeke et al.
Papers archive 2025-07-28
3 shown of 3, 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.
-
Adversarial Privacy Preservation in MRI Scans of the Brain 1 Jan 2021 · 0 repositories
-
Beyond COVID-19 Diagnosis: Prognosis with Hierarchical Graph Representation Learning 1 Jan 2021 · 0 repositories
-
SCAN: Learning to Classify Images without Labels 25 May 2020 · 2 repositories · arXiv:2005.12320
Tasks archive 2025-07-28
15 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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