A common architectural choice for deep metric learning is a convolutional neural network
followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to …

Metric learning seeks to embed images of objects such that class-defined relations are
captured by the embedding space. However, variability in images is not just due to different …

Recent studies have shown that many deep metric learning loss functions perform very
similarly under the same experimental conditions. One potential reason for this unexpected …

Deep metric learning papers from the past four years have consistently claimed great
advances in accuracy, often more than doubling the performance of decade-old methods. In …

Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-
/inter-class proximity violations in the embedding space. We relate DML to feasibility …

How do the neural networks distinguish two images? It is of critical importance to understand
the matching mechanism of deep models for developing reliable intelligent systems for …

The modern image search system requires semantic understanding of image, and a key yet
under-addressed problem is to learn a good metric for measuring the similarity between …

Metric learning involves learning a discriminative representation such that embeddings of
similar classes are encouraged to be close, while embeddings of dissimilar classes are …

The core of deep metric learning (DML) involves learning visual similarities in high-
dimensional embedding space. One of the main challenges is to generalize from seen …

Deep metric learning, in which the loss function plays a key role, has proven to be extremely
useful in visual recognition tasks. However, existing deep metric learning loss functions such …