Improved Deep Metric Learning with Multi-class N-pair Loss Objective

Explore this paper's citation graph

Summary

This paper proposes a new metric learning objective called multi-class N-pair loss, which generalizes triplet loss by allowing joint comparison among more than one negative examples and reduces the computational burden of evaluating deep embedding vectors via an efficient batch construction strategy using only N pairs of examples.

Type
article
Published
2016-12-05
Cited by
2,505
References
32

Keywords

Deep learning, Metric (unit), Computer science, Embedding, Benchmark (surveying)

References

Cited by

Related papers