Viet-Anh on Software Logo

What is: Semantic Clustering by Adopting Nearest Neighbours?

SourceSCAN: Learning to Classify Images without Labels
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

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.