# SVDNet for Pedestrian Retrieval

arXiv: https://arxiv.org/abs/1703.05693 · HTML: https://mlsanity.com/paper/1703.05693/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2017.

## Built on by (most cited first, 30 of 43)

- [NFormer: Robust Person Re-identification with Neighbor Transformer](https://mlsanity.com/paper/2204.09331/) (2022)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [Orthogonal Projection Loss](https://mlsanity.com/paper/2103.14021/) (2021)
- [Towards Discriminative Representation Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2108.03439/) (2021)
- [Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization](https://mlsanity.com/paper/2211.05296/) (2022)
- [From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization](https://mlsanity.com/paper/2503.00938/) (2025)
- [Graph-based Person Signature for Person Re-Identifications](https://mlsanity.com/paper/2104.06770/) (2021)
- [Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales](https://mlsanity.com/paper/2103.11781/) (2021)
- [Graph Convolution Based Efficient Re-Ranking for Visual Retrieval](https://mlsanity.com/paper/2306.08792/) (2023)
- [Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.05820/) (2022)
- [ES-Net: Erasing Salient Parts to Learn More in Re-Identification](https://mlsanity.com/paper/2103.05918/) (2021)
- [Graph Convolution for Re-ranking in Person Re-identification](https://mlsanity.com/paper/2107.02220/) (2021)
- [Rethinking Person Re-Identification via Semantic-Based Pretraining](https://mlsanity.com/paper/2110.05074/) (2021)
- [Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification](https://mlsanity.com/paper/2405.17790/) (2024)
- [From Attributes to Natural Language: A Survey and Foresight on Text-based Person Re-identification](https://mlsanity.com/paper/2408.00096/) (2024)
- [Disentangled Representations for Short-Term and Long-Term Person Re-Identification](https://mlsanity.com/paper/2409.05277/) (2024)
- [Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification](https://mlsanity.com/paper/2102.09321/) (2021)
- [Uncertainty Aware Multitask Pyramid Vision Transformer For UAV-Based Object Re-Identification](https://mlsanity.com/paper/2209.08686/) (2022)
- [Distortion-Disentangled Contrastive Learning](https://mlsanity.com/paper/2303.05066/) (2023)
- [HashReID: Dynamic Network with Binary Codes for Efficient Person Re-identification](https://mlsanity.com/paper/2308.11900/) (2023)
- [Towards Efficient Object Re-Identification with A Novel Cloud-Edge Collaborative Framework](https://mlsanity.com/paper/2401.02041/) (2024)
- [CLIP-SCGI: Synthesized Caption-Guided Inversion for Person Re-Identification](https://mlsanity.com/paper/2410.09382/) (2024)
- [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)
- [Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2112.07966/) (2021)
- [Data Augmentation in Human-Centric Vision](https://mlsanity.com/paper/2403.08650/) (2024)
- [Global-Local Dynamic Feature Alignment Network for Person Re-Identification](https://mlsanity.com/paper/2109.05759/) (2021)
- [Stronger Baseline for Person Re-Identification](https://mlsanity.com/paper/2112.01059/) (2021)
- [Pixel-wise Graph Attention Networks for Person Re-identification](https://mlsanity.com/paper/2307.09183/) (2023)
- [SphOR: A Representation Learning Perspective on Open-set Recognition for Identifying Unknown Classes in Deep Learning Models](https://mlsanity.com/paper/2503.08049/) (2025)

## Abstract (arXiv)

This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID). We view each weight vector within a fully connected (FC) layer in a convolutional neuron network (CNN) as a projection basis. It is observed that the weight vectors are usually highly correlated. This problem leads to correlations among entries of the FC descriptor, and compromises the retrieval performance based on the Euclidean distance. To address the problem, this paper proposes to optimize the deep representation learning process with Singular Vector Decomposition (SVD). Specifically, with the restraint and relaxation iteration (RRI) training scheme, we are able to iteratively integrate the orthogonality constraint in CNN training, yielding the so-called SVDNet. We conduct experiments on the Market-1501, CUHK03, and Duke datasets, and show that RRI effectively reduces the correlation among the projection vectors, produces more discriminative FC descriptors, and significantly improves the re-ID accuracy. On the Market-1501 dataset, for instance, rank-1 accuracy is improved from 55.3% to 80.5% for CaffeNet, and from 73.8% to 82.3% for ResNet-50.