LatentCLR
Produced by LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions
Contrastive learning
A family of learning algorithms that forms representations by comparing samples designated as similar or dissimilar.
A family of learning algorithms that forms representations by comparing samples designated as similar or dissimilar.
Its objective brings selected pairs together while separating alternatives according to a sampling and similarity design.