# Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss

arXiv: https://arxiv.org/abs/2008.09880 · HTML: https://mlsanity.com/paper/2008.09880/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2020.

## Built on by (most cited first, 10 of 10)

- [Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes](https://mlsanity.com/paper/2407.10957/) (2024)
- [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)
- [Contrastive Bayesian Analysis for Deep Metric Learning](https://mlsanity.com/paper/2210.04402/) (2022)
- [Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signals](https://mlsanity.com/paper/2308.04650/) (2023)
- [Piecewise-Linear Manifolds for Deep Metric Learning](https://mlsanity.com/paper/2403.14977/) (2024)
- [Color Variants Identification in Fashion e-commerce via Contrastive Self-Supervised Representation Learning](https://mlsanity.com/paper/2104.08581/) (2021)
- [A Tale of Color Variants: Representation and Self-Supervised Learning in Fashion E-Commerce](https://mlsanity.com/paper/2112.02910/) (2021)
- [Regressing Relative Fine-Grained Change for Sub-Groups in Unreliable Heterogeneous Data Through Deep Multi-Task Metric Learning](https://mlsanity.com/paper/2208.05800/) (2022)
- [Towards Adversarially Robust Deep Metric Learning](https://mlsanity.com/paper/2501.01025/) (2025)

## Abstract (arXiv)

Metric learning is an important problem in machine learning. It aims to group similar examples together. Existing state-of-the-art metric learning approaches require class labels to learn a metric. As obtaining class labels in all applications is not feasible, we propose an unsupervised approach that learns a metric without making use of class labels. The lack of class labels is compensated by obtaining pseudo-labels of data using a graph-based clustering approach. The pseudo-labels are used to form triplets of examples, which guide the metric learning. We propose a probabilistic loss that minimizes the chances of each triplet violating an angular constraint. A weight function, and an orthogonality constraint in the objective speeds up the convergence and avoids a model collapse. We also provide a stochastic formulation of our method to scale up to large-scale datasets. Our studies demonstrate the competitiveness of our approach against state-of-the-art methods. We also thoroughly study the effect of the different components of our method.