# Scalable Person Re-identification on Supervised Smoothed Manifold

arXiv: https://arxiv.org/abs/1703.08359 · HTML: https://mlsanity.com/paper/1703.08359/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2017.

## Built on by (most cited first, 24 of 24)

- [Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification](https://mlsanity.com/paper/2104.14913/) (2021)
- [CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2101.08467/) (2021)
- [Implicit Sample Extension for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2204.06892/) (2022)
- [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)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID](https://mlsanity.com/paper/2305.12673/) (2023)
- [Learning Multi-Attention Context Graph for Group-Based Re-Identification](https://mlsanity.com/paper/2104.14236/) (2021)
- [Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2207.13035/) (2022)
- [Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification](https://mlsanity.com/paper/2203.01723/) (2022)
- [CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification](https://mlsanity.com/paper/2311.10605/) (2023)
- [Video Person Re-identification using Attribute-enhanced Features](https://mlsanity.com/paper/2108.06946/) (2021)
- [Graph Convolution for Re-ranking in Person Re-identification](https://mlsanity.com/paper/2107.02220/) (2021)
- [A Brief Survey on Person Recognition at a Distance](https://mlsanity.com/paper/2212.08969/) (2022)
- [Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition](https://mlsanity.com/paper/2103.16889/) (2021)
- [Pose Invariant Person Re-Identification using Robust Pose-transformation GAN](https://mlsanity.com/paper/2105.00930/) (2021)
- [FPB: Feature Pyramid Branch for Person Re-Identification](https://mlsanity.com/paper/2108.01901/) (2021)
- [Confidence-guided Centroids for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2211.11921/) (2022)
- [Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification](https://mlsanity.com/paper/2104.13780/) (2021)
- [Large-scale Fully-Unsupervised Re-Identification](https://mlsanity.com/paper/2307.14278/) (2023)
- [Adaptive Intra-Class Variation Contrastive Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2404.04665/) (2024)
- [Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification](https://mlsanity.com/paper/2105.03042/) (2021)
- [Domain Camera Adaptation and Collaborative Multiple Feature Clustering for Unsupervised Person Re-ID](https://mlsanity.com/paper/2208.08624/) (2022)
- [Mutimodal Ranking Optimization for Heterogeneous Face Re-identification](https://mlsanity.com/paper/2212.05510/) (2022)

## Abstract (arXiv)

Most existing person re-identification algorithms either extract robust visual features or learn discriminative metrics for person images. However, the underlying manifold which those images reside on is rarely investigated. That raises a problem that the learned metric is not smooth with respect to the local geometry structure of the data manifold. In this paper, we study person re-identification with manifold-based affinity learning, which did not receive enough attention from this area. An unconventional manifold-preserving algorithm is proposed, which can 1) make the best use of supervision from training data, whose label information is given as pairwise constraints; 2) scale up to large repositories with low on-line time complexity; and 3) be plunged into most existing algorithms, serving as a generic postprocessing procedure to further boost the identification accuracies. Extensive experimental results on five popular person re-identification benchmarks consistently demonstrate the effectiveness of our method. Especially, on the largest CUHK03 and Market-1501, our method outperforms the state-of-the-art alternatives by a large margin with high efficiency, which is more appropriate for practical applications.