# Feature Representation in Deep Metric Embeddings

arXiv: https://arxiv.org/abs/2102.03176 · HTML: https://mlsanity.com/paper/2102.03176/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 36 references that are in the map.
- First posted on arXiv 5 Feb 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [RepMet: Representative-based metric learning for classification and one-shot object detection](https://mlsanity.com/paper/1806.04728/) (2018)
- [One-shot Learning with Memory-Augmented Neural Networks](https://mlsanity.com/paper/1605.06065/) (2016)
- [One-Shot Generalization in Deep Generative Models](https://mlsanity.com/paper/1603.05106/) (2016)
- [Targeting Ultimate Accuracy: Face Recognition via Deep Embedding](https://mlsanity.com/paper/1506.07310/) (2015)

## Abstract (arXiv)

In deep metric learning (DML), high-level input data are represented in a lower-level representation (embedding) space, such that samples from the same class are mapped close together, while samples from disparate classes are mapped further apart. In this lower-level representation, only a single inference sample from each known class is required to discriminate between classes accurately. The features a DML model uses to discriminate between classes and the importance of each feature in the training process are unknown. To investigate this, this study takes embeddings trained to discriminate faces (identities) and uses unsupervised clustering to identify the features involved in facial identity discrimination by examining their representation within the embedded space. This study is split into two cases; intra class sub-discrimination, where attributes that differ between a single identity are considered; such as beards and emotions; and extra class sub-discrimination, where attributes which differ between different identities/people, are considered; such as gender, skin tone and age. In the intra class scenario, the inference process distinguishes common attributes between single identities, achieving 90.0% and 76.0% accuracy for beards and glasses, respectively. The system can also perform extra class sub-discrimination with a high accuracy rate, notably 99.3%, 99.3% and 94.1% for gender, skin tone, and age, respectively.