Rethinking preventing class-collapsing in metric learning with margin-based losses
Rethinking preventing class-collapsing in metric learning with margin-based losses
Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct sub-clusters are present. Although theoretically with optimal assumptions, margin-based losses such as the triplet loss and margin loss …