Nearest neighbor search

Linguistics

Engineering

Philosophy

Biology

Identification (biology)

Discrete mathematics

Similarity (geometry)

Economics

Set (abstract data type)

Computer science

Botany

Simple (philosophy)

Embedding

Softmax function

k-nearest neighbors algorithm

Pattern recognition (psychology)

Metric space

Mathematics

Image (mathematics)

Feature vector

Feature (linguistics)

Epistemology

Cosine similarity

Mathematical analysis

Operations management

Artificial intelligence

Programming language

Deep learning

Metric (unit)

Generalization

Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.

Deep Cosine Metric Learning for Person Re-identification