# SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

arXiv: https://arxiv.org/abs/1807.00537 · HTML: https://mlsanity.com/paper/1807.00537/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

## Built on by (most cited first, 27 of 27)

- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [AutoLoss: Automated Loss Function Search in Recommendations](https://mlsanity.com/paper/2106.06713/) (2021)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking](https://mlsanity.com/paper/2407.13646/) (2024)
- [Self-Regulation for Semantic Segmentation](https://mlsanity.com/paper/2108.09702/) (2021)
- [MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2110.11264/) (2021)
- [Curved Geometric Networks for Visual Anomaly Recognition](https://mlsanity.com/paper/2208.01188/) (2022)
- [Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations](https://mlsanity.com/paper/2306.02092/) (2023)
- [Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples](https://mlsanity.com/paper/2311.15571/) (2023)
- [Keypoint Message Passing for Video-based Person Re-Identification](https://mlsanity.com/paper/2111.08279/) (2021)
- [Identification of Attack-Specific Signatures in Adversarial Examples](https://mlsanity.com/paper/2110.06802/) (2021)
- [Specialized Re-Ranking: A Novel Retrieval-Verification Framework for Cloth Changing Person Re-Identification](https://mlsanity.com/paper/2210.03592/) (2022)
- [On The Distribution of Penultimate Activations of Classification Networks](https://mlsanity.com/paper/2107.01900/) (2021)
- [Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2204.04842/) (2022)
- [DiP: Learning Discriminative Implicit Parts for Person Re-Identification](https://mlsanity.com/paper/2212.13906/) (2022)
- [Learning Multi-Manifold Embedding for Out-Of-Distribution Detection](https://mlsanity.com/paper/2409.12479/) (2024)
- [FPB: Feature Pyramid Branch for Person Re-Identification](https://mlsanity.com/paper/2108.01901/) (2021)
- [Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2112.07966/) (2021)
- [Stronger Baseline for Person Re-Identification](https://mlsanity.com/paper/2112.01059/) (2021)
- [Provably Valid and Diverse Mutations of Real-World Media Data for DNN Testing](https://mlsanity.com/paper/2112.01956/) (2021)
- [Automated Side Channel Analysis of Media Software with Manifold Learning](https://mlsanity.com/paper/2112.04947/) (2021)
- [An Efficient Person Clustering Algorithm for Open Checkout-free Groceries](https://mlsanity.com/paper/2208.02973/) (2022)
- [Leaning Compact and Representative Features for Cross-Modality Person Re-Identification](https://mlsanity.com/paper/2103.14210/) (2021)
- [Scalable Vehicle Re-Identification via Self-Supervision](https://mlsanity.com/paper/2205.07613/) (2022)
- [Benchmarking person re-identification datasets and approaches for practical real-world implementations](https://mlsanity.com/paper/2212.09981/) (2022)
- [Joint Discriminative and Metric Embedding Learning for Person Re-Identification](https://mlsanity.com/paper/2212.14107/) (2022)
- [Mutual Distillation Learning For Person Re-Identification](https://mlsanity.com/paper/2401.06430/) (2024)

## Abstract (arXiv)

Many current successful Person Re-Identification(ReID) methods train a model with the softmax loss function to classify images of different persons and obtain the feature vectors at the same time. However, the underlying feature embedding space is ignored. In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously. A balanced sampling strategy is also introduced. Finally, we propose a convolutional neural network called SphereReID adopting Sphere Softmax and training a single model end-to-end with a new warming-up learning rate schedule on four challenging datasets including Market-1501, DukeMTMC-reID, CHHK-03, and CUHK-SYSU. Experimental results demonstrate that this single model outperforms the state-of-the-art methods on all four datasets without fine-tuning or re-ranking. For example, it achieves 94.4% rank-1 accuracy on Market-1501 and 83.9% rank-1 accuracy on DukeMTMC-reID. The code and trained weights of our model will be released.