# Large-scale Distance Metric Learning with Uncertainty

arXiv: https://arxiv.org/abs/1805.10384 · HTML: https://mlsanity.com/paper/1805.10384/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2018.

## Built on by (most cited first, 4 of 4)

- [Unsupervised Visual Representation Learning by Online Constrained K-Means](https://mlsanity.com/paper/2105.11527/) (2021)
- [Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.05820/) (2022)
- [Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance](https://mlsanity.com/paper/2207.09336/) (2022)
- [Deep Metric Learning for Unsupervised Remote Sensing Change Detection](https://mlsanity.com/paper/2303.09536/) (2023)

## Abstract (arXiv)

Distance metric learning (DML) has been studied extensively in the past decades for its superior performance with distance-based algorithms. Most of the existing methods propose to learn a distance metric with pairwise or triplet constraints. However, the number of constraints is quadratic or even cubic in the number of the original examples, which makes it challenging for DML to handle the large-scale data set. Besides, the real-world data may contain various uncertainty, especially for the image data. The uncertainty can mislead the learning procedure and cause the performance degradation. By investigating the image data, we find that the original data can be observed from a small set of clean latent examples with different distortions. In this work, we propose the margin preserving metric learning framework to learn the distance metric and latent examples simultaneously. By leveraging the ideal properties of latent examples, the training efficiency can be improved significantly while the learned metric also becomes robust to the uncertainty in the original data. Furthermore, we can show that the metric is learned from latent examples only, but it can preserve the large margin property even for the original data. The empirical study on the benchmark image data sets demonstrates the efficacy and efficiency of the proposed method.