Improving Calibration in Deep Metric Learning With Cross-Example Softmax

Understand

Modern image retrieval systems increasingly rely on the use of deep neural networks to learn embedding spaces in which distance encodes the relevance between a given query and image.

• In this setting, existing approaches tend to emphasize one of two properties.
• Triplet-based methods capture top-$k$ relevancy, where all top-$k$ scoring documents are assumed to be relevant to a given query Pairwise contrastive models capture threshold relevancy, where all documents scoring higher than some threshold are assumed to be relevant.
• In this paper, we propose Cross-Example Softmax which combines the properties of top-$k$ and threshold relevancy.