# Joint Discriminative and Metric Embedding Learning for Person Re-Identification

arXiv: https://arxiv.org/abs/2212.14107 · HTML: https://mlsanity.com/paper/2212.14107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 28 Dec 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [Part-Aligned Bilinear Representations for Person Re-identification](https://mlsanity.com/paper/1804.07094/) (2018)
- [Interaction-and-Aggregation Network for Person Re-identification](https://mlsanity.com/paper/1907.08435/) (2019)
- [A Discriminatively Learned CNN Embedding for Person Re-identification](https://mlsanity.com/paper/1611.05666/) (2016)
- [FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification](https://mlsanity.com/paper/1810.02936/) (2018)
- [Pose-Normalized Image Generation for Person Re-identification](https://mlsanity.com/paper/1712.02225/) (2017)
- [Deeply-Learned Part-Aligned Representations for Person Re-Identification](https://mlsanity.com/paper/1707.07256/) (2017)
- [AANet: Attribute Attention Network for Person Re-Identifications](https://mlsanity.com/paper/1912.09021/) (2019)
- [Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification](https://mlsanity.com/paper/1710.06555/) (2017)
- [Person Re-identification with Deep Similarity-Guided Graph Neural Network](https://mlsanity.com/paper/1807.09975/) (2018)
- [Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification](https://mlsanity.com/paper/1604.07528/) (2016)
- [SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification](https://mlsanity.com/paper/1807.00537/) (2018)
- [Learning a Discriminative Null Space for Person Re-identification](https://mlsanity.com/paper/1603.02139/) (2016)
- [Attributes-aided Part Detection and Refinement for Person Re-identification](https://mlsanity.com/paper/1902.10528/) (2019)
- [CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification](https://mlsanity.com/paper/1811.07544/) (2018)

## Abstract (arXiv)

Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations such as pose, illumination, viewpoint, background, and sensor noise. Recent approaches postulate that powerful architectures have the capacity to learn feature representations invariant to nuisance factors, by training them with losses that minimize intra-class variance and maximize inter-class separation, without modeling nuisance factors explicitly. The dominant approaches use either a discriminative loss with margin, like the softmax loss with the additive angular margin, or a metric learning loss, like the triplet loss with batch hard mining of triplets. Since the softmax imposes feature normalization, it limits the gradient flow supervising the feature embedding. We address this by joining the losses and leveraging the triplet loss as a proxy for the missing gradients. We further improve invariance to nuisance factors by adding the discriminative task of predicting attributes. Our extensive evaluation highlights that when only a holistic representation is learned, we consistently outperform the state-of-the-art on the three most challenging datasets. Such representations are easier to deploy in practical systems. Finally, we found that joining the losses removes the requirement for having a margin in the softmax loss while increasing performance.