Deep Metric Learning via Facility Location

Abstract

Learning image similarity metrics in an end-to-end fashion with deep networks has demonstrated excellent results on tasks such as clustering and retrieval. However, current methods, all focus on a very local view of the data. In this paper, we propose a new metric learning scheme, based on structured prediction, that is aware of the global structure of the embedding space, and which is designed to optimize a clustering quality metric (NMI). We show state of the art performance on standard datasets, such as CUB200-2011, Cars196, and Stanford online products on NMI and R@K evaluation metrics.

Cite

Text

Song et al. "Deep Metric Learning via Facility Location." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.237

Markdown

[Song et al. "Deep Metric Learning via Facility Location." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/song2017cvpr-deep/) doi:10.1109/CVPR.2017.237

BibTeX

@inproceedings{song2017cvpr-deep,
  title     = {{Deep Metric Learning via Facility Location}},
  author    = {Song, Hyun Oh and Jegelka, Stefanie and Rathod, Vivek and Murphy, Kevin},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.237},
  url       = {https://mlanthology.org/cvpr/2017/song2017cvpr-deep/}
}