# Hardness-Aware Deep Metric Learning

arXiv: https://arxiv.org/abs/1903.05503 · HTML: https://mlsanity.com/paper/1903.05503/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2019.

## Built on by (most cited first, 30 of 55)

- [Topology-Imbalance Learning for Semi-Supervised Node Classification](https://mlsanity.com/paper/2110.04099/) (2021)
- [A Primer on Pretrained Multilingual Language Models](https://mlsanity.com/paper/2107.00676/) (2021)
- [Recall@k Surrogate Loss with Large Batches and Similarity Mixup](https://mlsanity.com/paper/2108.11179/) (2021)
- [Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation](https://mlsanity.com/paper/2304.02970/) (2023)
- [Non-isotropy Regularization for Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2203.08547/) (2022)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Towards Interpretable Deep Metric Learning with Structural Matching](https://mlsanity.com/paper/2108.05889/) (2021)
- [It Takes Two to Tango: Mixup for Deep Metric Learning](https://mlsanity.com/paper/2106.04990/) (2021)
- [Deep Relational Metric Learning](https://mlsanity.com/paper/2108.10026/) (2021)
- [Learning with Memory-based Virtual Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.16940/) (2021)
- [Integrating Language Guidance into Vision-based Deep Metric Learning](https://mlsanity.com/paper/2203.08543/) (2022)
- [A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2207.03784/) (2022)
- [Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.15454/) (2021)
- [Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning](https://mlsanity.com/paper/2107.09562/) (2021)
- [Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.06812/) (2022)
- [Attributable Visual Similarity Learning](https://mlsanity.com/paper/2203.14932/) (2022)
- [Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning](https://mlsanity.com/paper/2203.12748/) (2022)
- [Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation](https://mlsanity.com/paper/2107.01079/) (2021)
- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)
- [Contrastive Bayesian Analysis for Deep Metric Learning](https://mlsanity.com/paper/2210.04402/) (2022)
- [LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning](https://mlsanity.com/paper/2108.09335/) (2021)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [Efficient Malware Analysis Using Metric Embeddings](https://mlsanity.com/paper/2212.02663/) (2022)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [DAS: Densely-Anchored Sampling for Deep Metric Learning](https://mlsanity.com/paper/2208.00119/) (2022)
- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [Exploring Adversarial Robustness of Deep Metric Learning](https://mlsanity.com/paper/2102.07265/) (2021)
- [Pairwise Similarity Learning is SimPLE](https://mlsanity.com/paper/2310.09449/) (2023)
- [Anchor-aware Deep Metric Learning for Audio-visual Retrieval](https://mlsanity.com/paper/2404.13789/) (2024)
- [From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning](https://mlsanity.com/paper/2406.15044/) (2024)

## Abstract (arXiv)

This paper presents a hardness-aware deep metric learning (HDML) framework. Most previous deep metric learning methods employ the hard negative mining strategy to alleviate the lack of informative samples for training. However, this mining strategy only utilizes a subset of training data, which may not be enough to characterize the global geometry of the embedding space comprehensively. To address this problem, we perform linear interpolation on embeddings to adaptively manipulate their hard levels and generate corresponding label-preserving synthetics for recycled training, so that information buried in all samples can be fully exploited and the metric is always challenged with proper difficulty. Our method achieves very competitive performance on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.