# Hierarchical Relationship Alignment Metric Learning

arXiv: https://arxiv.org/abs/2103.15107 · HTML: https://mlsanity.com/paper/2103.15107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 28 Mar 2021.

## Builds on (most cited first, 8 of 8)

- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Deep Metric Learning with Hierarchical Triplet Loss](https://mlsanity.com/paper/1810.06951/) (2018)
- [Deep Metric Learning with Angular Loss](https://mlsanity.com/paper/1708.01682/) (2017)
- [Geometric Mean Metric Learning](https://mlsanity.com/paper/1607.05002/) (2016)
- [A Kernel Classification Framework for Metric Learning](https://mlsanity.com/paper/1309.5823/) (2013)

## Abstract (arXiv)

Most existing metric learning methods focus on learning a similarity or distance measure relying on similar and dissimilar relations between sample pairs. However, pairs of samples cannot be simply identified as similar or dissimilar in many real-world applications, e.g., multi-label learning, label distribution learning. To this end, relation alignment metric learning (RAML) framework is proposed to handle the metric learning problem in those scenarios. But RAML learn a linear metric, which can't model complex datasets. Combining with deep learning and RAML framework, we propose a hierarchical relationship alignment metric leaning model HRAML, which uses the concept of relationship alignment to model metric learning problems under multiple learning tasks, and makes full use of the consistency between the sample pair relationship in the feature space and the sample pair relationship in the label space. Further we organize several experiment divided by learning tasks, and verified the better performance of HRAML against many popular methods and RAML framework.