# A Simple and Effective Framework for Pairwise Deep Metric Learning

arXiv: https://arxiv.org/abs/1912.11194 · HTML: https://mlsanity.com/paper/1912.11194/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2019.

## Built on by (most cited first, 13 of 13)

- [Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence](https://mlsanity.com/paper/2104.08736/) (2021)
- [Rank-based Decomposable Losses in Machine Learning: A Survey](https://mlsanity.com/paper/2207.08768/) (2022)
- [Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions](https://mlsanity.com/paper/2106.07451/) (2021)
- [Stochastic Constrained DRO with a Complexity Independent of Sample Size](https://mlsanity.com/paper/2210.05740/) (2022)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [Learning Distributionally Robust Models at Scale via Composite Optimization](https://mlsanity.com/paper/2203.09607/) (2022)
- [Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning](https://mlsanity.com/paper/2406.05686/) (2024)
- [Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images](https://mlsanity.com/paper/2407.09694/) (2024)
- [AdFair-CLIP: Adversarial Fair Contrastive Language-Image Pre-training for Chest X-rays](https://mlsanity.com/paper/2506.23467/) (2025)
- [FedDRO: Federated Compositional Optimization for Distributionally Robust Learning](https://mlsanity.com/paper/2311.12652/) (2023)
- [Fairness via Adversarial Attribute Neighbourhood Robust Learning](https://mlsanity.com/paper/2210.06630/) (2022)
- [Robust Long-Tailed Learning via Label-Aware Bounded CVaR](https://mlsanity.com/paper/2308.15405/) (2023)
- [Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric](https://mlsanity.com/paper/2407.03106/) (2024)

## Abstract (arXiv)

Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we cast DML as a simple pairwise binary classification problem that classifies a pair of examples as similar or dissimilar. It identifies the most critical issue in this problem--imbalanced data pairs. To tackle this issue, we propose a simple and effective framework to sample pairs in a batch of data for updating the model. The key to this framework is to define a robust loss for all pairs over a mini-batch of data, which is formulated by distributionally robust optimization. The flexibility in constructing the uncertainty decision set of the dual variable allows us to recover state-of-the-art complicated losses and also to induce novel variants. Empirical studies on several benchmark data sets demonstrate that our simple and effective method outperforms the state-of-the-art results. Codes are available at: https://github.com/qiqi-helloworld/A-Simple-and-Effective-Framework-for-Pairewise-Distance-Metric-Learning