# Deep Cosine Metric Learning for Person Re-Identification

arXiv: https://arxiv.org/abs/1812.00442 · HTML: https://mlsanity.com/paper/1812.00442/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2018.

## Built on by (most cited first, 30 of 73)

- [Global Tracking Transformers](https://mlsanity.com/paper/2203.13250/) (2022)
- [Incremental Few-Shot Instance Segmentation](https://mlsanity.com/paper/2105.05312/) (2021)
- [Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition](https://mlsanity.com/paper/2109.01305/) (2021)
- [Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths](https://mlsanity.com/paper/2108.10606/) (2021)
- [1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking](https://mlsanity.com/paper/2101.08040/) (2021)
- [Learning Triadic Belief Dynamics in Nonverbal Communication from Videos](https://mlsanity.com/paper/2104.02841/) (2021)
- [3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking](https://mlsanity.com/paper/2308.15316/) (2023)
- [Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification](https://mlsanity.com/paper/2203.15381/) (2022)
- [Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wild](https://mlsanity.com/paper/2309.08644/) (2023)
- [DROID: Driver-centric Risk Object Identification](https://mlsanity.com/paper/2106.13201/) (2021)
- [Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain Adaptation](https://mlsanity.com/paper/2401.00617/) (2024)
- [2rd Place Solutions in the HC-STVG track of Person in Context Challenge 2021](https://mlsanity.com/paper/2106.07166/) (2021)
- [Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation](https://mlsanity.com/paper/2108.03372/) (2021)
- [Transforming Gait: Video-Based Spatiotemporal Gait Analysis](https://mlsanity.com/paper/2203.09371/) (2022)
- [Track Targets by Dense Spatio-Temporal Position Encoding](https://mlsanity.com/paper/2210.09455/) (2022)
- [Multi-annotator Deep Learning: A Probabilistic Framework for Classification](https://mlsanity.com/paper/2304.02539/) (2023)
- [Distribution Shift Matters for Knowledge Distillation with Webly Collected Images](https://mlsanity.com/paper/2307.11469/) (2023)
- [Z-GMOT: Zero-shot Generic Multiple Object Tracking](https://mlsanity.com/paper/2305.17648/) (2023)
- [Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking](https://mlsanity.com/paper/2312.08951/) (2023)
- [Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking](https://mlsanity.com/paper/2405.18606/) (2024)
- [Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning](https://mlsanity.com/paper/2402.02340/) (2024)
- [Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection](https://mlsanity.com/paper/2207.06603/) (2022)
- [M3Act: Learning from Synthetic Human Group Activities](https://mlsanity.com/paper/2306.16772/) (2023)
- [TDIOT: Target-driven Inference for Deep Video Object Tracking](https://mlsanity.com/paper/2103.11017/) (2021)
- [BlinkTrack: Feature Tracking over 80 FPS via Events and Images](https://mlsanity.com/paper/2409.17981/) (2024)
- [MEX: Memory-efficient Approach to Referring Multi-Object Tracking](https://mlsanity.com/paper/2502.13875/) (2025)
- [Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm](https://mlsanity.com/paper/2103.06759/) (2021)
- [Similarity-Aware Fusion Network for 3D Semantic Segmentation](https://mlsanity.com/paper/2107.01579/) (2021)
- [Analyzing vehicle pedestrian interactions combining data cube structure and predictive collision risk estimation model](https://mlsanity.com/paper/2107.12507/) (2021)
- [Incremental cluster validity index-guided online learning for performance and robustness to presentation order](https://mlsanity.com/paper/2108.07743/) (2021)

## Abstract (arXiv)

Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.