# Deep Feature Learning with Relative Distance Comparison for Person Re-identification

arXiv: https://arxiv.org/abs/1512.03622 · HTML: https://mlsanity.com/paper/1512.03622/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2015.

## Built on by (most cited first, 25 of 25)

- [Solving Inefficiency of Self-supervised Representation Learning](https://mlsanity.com/paper/2104.08760/) (2021)
- [Feature Completion for Occluded Person Re-Identification](https://mlsanity.com/paper/2106.12733/) (2021)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Deeply-Coupled Convolution-Transformer with Spatial-temporal Complementary Learning for Video-based Person Re-identification](https://mlsanity.com/paper/2304.14122/) (2023)
- [Pose-driven Attention-guided Image Generation for Person Re-Identification](https://mlsanity.com/paper/2104.13773/) (2021)
- [Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey](https://mlsanity.com/paper/2201.09267/) (2022)
- [Online and Real-Time Tracking in a Surveillance Scenario](https://mlsanity.com/paper/2106.01153/) (2021)
- [Deep Ranking with Adaptive Margin Triplet Loss](https://mlsanity.com/paper/2107.06187/) (2021)
- [Learning Instance-level Spatial-Temporal Patterns for Person Re-identification](https://mlsanity.com/paper/2108.00171/) (2021)
- [Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval](https://mlsanity.com/paper/2204.09730/) (2022)
- [PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification](https://mlsanity.com/paper/2207.04793/) (2022)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching](https://mlsanity.com/paper/2203.15285/) (2022)
- [Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval](https://mlsanity.com/paper/2212.04267/) (2022)
- [Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identification](https://mlsanity.com/paper/2304.09498/) (2023)
- [Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification](https://mlsanity.com/paper/2104.13780/) (2021)
- [Unsupervised clothing change adaptive person ReID](https://mlsanity.com/paper/2109.03702/) (2021)
- [Co-segmentation Inspired Attention Module for Video-based Computer Vision Tasks](https://mlsanity.com/paper/2111.07370/) (2021)
- [Person detection and re-identification in open-world settings of retail stores and public spaces](https://mlsanity.com/paper/2505.00772/) (2025)
- [Self-Supervised Pretraining of Graph Neural Network for the Retrieval of Related Mathematical Expressions in Scientific Articles](https://mlsanity.com/paper/2209.00446/) (2022)
- [Combining Two Adversarial Attacks Against Person Re-Identification Systems](https://mlsanity.com/paper/2309.13763/) (2023)
- [Contrastive Multiple Instance Learning for Weakly Supervised Person ReID](https://mlsanity.com/paper/2402.07685/) (2024)
- [The Research of Group Re-identification from Multiple Cameras](https://mlsanity.com/paper/2407.14620/) (2024)
- [Locality-Sensitive Hashing for Efficient Hard Negative Sampling in Contrastive Learning](https://mlsanity.com/paper/2505.17844/) (2025)
- [Improving Generalization in Deepfake Detection with Face Foundation Models and Metric Learning](https://mlsanity.com/paper/2508.19730/) (2025)

## Abstract (arXiv)

Identifying the same individual across different scenes is an important yet difficult task in intelligent video surveillance. Its main difficulty lies in how to preserve similarity of the same person against large appearance and structure variation while discriminating different individuals. In this paper, we present a scalable distance driven feature learning framework based on the deep neural network for person re-identification, and demonstrate its effectiveness to handle the existing challenges. Specifically, given the training images with the class labels (person IDs), we first produce a large number of triplet units, each of which contains three images, i.e. one person with a matched reference and a mismatched reference. Treating the units as the input, we build the convolutional neural network to generate the layered representations, and follow with the L2 distance metric. By means of parameter optimization, our framework tends to maximize the relative distance between the matched pair and the mismatched pair for each triplet unit. Moreover, a nontrivial issue arising with the framework is that the triplet organization cubically enlarges the number of training triplets, as one image can be involved into several triplet units. To overcome this problem, we develop an effective triplet generation scheme and an optimized gradient descent algorithm, making the computational load mainly depends on the number of original images instead of the number of triplets. On several challenging databases, our approach achieves very promising results and outperforms other state-of-the-art approaches.