Reducing Class Collapse in Metric Learning with Easy Positive Sampling

Cited by: 0|Bibtex|Views105
Other Links: arxiv.org

Abstract:

Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learn representation can be sub-optimal when the distribution of intra-class samples is diverse and distinct sub-clusters are present. We theoretically prove and empirically show that under reasonable noise assu...More

Code:

Data:

Your rating :
0

 

Tags
Comments