Learning a Discriminative Null Space for Person Re-identification

@article{Zhang2016LearningAD,
  title={Learning a Discriminative Null Space for Person Re-identification},
  author={Li Zhang and Tao Xiang and Shaogang Gong},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={1239-1248}
}
  • Li Zhang, T. Xiang, S. Gong
  • Published 2016
  • Computer Science, Mathematics
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views. Typically a person's appearance is represented using features of thousands of dimensions, whilst only hundreds of training samples are available due to the difficulties in collecting matched training images. With the number of training samples much smaller than the feature dimension, the existing methods thus face the classic small sample size (SSS) problem and have to… Expand
A discriminative null space based deep learning approach for person re-identification
TLDR
This paper designs a discriminative null space based deep learning approach for person re-identification and adopts the Null Foley-Sammon Transform (NFST) metric learning approach to combine the low-level, mid-level features and high- level features learned by the SCNN in a new discriminatives null space. Expand
Person re-identification by integrating metric learning and support vector machine
TLDR
A joint learning method by integrating the discriminative metric learning, the support vector machine (SVM) and the identity discriminator into one model, so as to realize joint construction of metric learning and identity discriminators is proposed. Expand
A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-Identification
  • T. Ali, S. Chaudhuri
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
  • 2019
TLDR
This paper proposes a semi-supervised metric learning approach that can utilize information in unlabelled data with the help of a few labelled training samples and addresses the small sample size problem that inherently occurs due to the few labeled training data. Expand
Sample Specific Multi-Kernel Metric Learning for Person Re-identification
  • Jun Fang, Rufei Zhang, Feng Jiang
  • Computer Science
  • Proceedings of the 2nd International Conference on Electrical and Electronic Engineering (EEE 2019)
  • 2019
TLDR
The existing metric learning based Person Re-Identification are challenged with large appearance variations across non-overlapping cameras and the proposed approach outperforms most non-deep-learning based approaches on popular benchmarks including VIPeR, GRID and CUHK0. Expand
Person re-identification by kernel null space marginal Fisher analysis
TLDR
This work proposes to embed samples into a discriminative null space based on Marginal Fisher Analysis (MFA) to overcome the SSS problem and extends the proposed method to kernel version, which is called Kernel Null Space Marginal Fischer Analysis (KNSMFA). Expand
Deep adaptive feature embedding with local sample distributions for person re-identification
TLDR
A novel objective function is proposed to jointly optimize similarity metric learning, local positive mining and robust deep feature embedding for person re-id by proposing a novel sampling to mine suitable positives within a local range to improve the deep embedding in the context of large intra-class variations. Expand
Towards fast and kernelized orthogonal discriminant analysis on person re-identification
TLDR
This paper proposes to solve the singularity problem by employing the pseudo-inverse of the within-class scatter matrix and learning an orthogonal transformation for the metric, and develops a kernel version against non-linearity in person re-identification, and a fast version for more efficient solution. Expand
Co-Metric Learning for Person Re-Identification
TLDR
A novel semisupervised co-metric learning framework is proposed to learn a discriminative Mahalanobis-like distance matrix for label-insufficient person re-identification. Expand
LPCV: Learning projections from corresponding views for person re-identification
  • Hong Liu, Qiao Guan
  • Mathematics, Computer Science
  • 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
TLDR
This work proposes a novel method to learn projections from corresponding views (LPCV) for person re-identification, which significantly performs favorably against the state-of-the-art methods, especially on the rank-1 matching rate. Expand
Equidistance constrained metric learning for person re-identification
TLDR
An algorithm for learning a Mahalanobis distance for person re-identification that outperforms the state-of-the-art methods on CUHK01, CUHK03, Market1501 and DukeMTMC-reID datasets, and achieves very competitive performance on the widely used VIPeR dataset. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
Person Re-Identification by Support Vector Ranking
TLDR
This work converts the person re-identification problem from an absolute scoring p roblem to a relative ranking problem and develops an novel Ensemble RankSVM to overcome the scalability limitation problem suffered by existing SVM-based ranking methods. Expand
Local Fisher Discriminant Analysis for Pedestrian Re-identification
TLDR
A novel approach to the pedestrian re-identification problem that uses metric learning to improve the state-of-the-art performance on standard public datasets and is an effective way to process observations comprising multiple shots, and is non-iterative: the computation times are relatively modest. Expand
Person Re-identification by Descriptive and Discriminative Classification
TLDR
The proposed approach is demonstrated on two datasets, where it is shown that the combination of a generic descriptive statistical model and a discriminatively learned feature-based model attains considerably better results than the individual models alone. Expand
Semi-supervised Coupled Dictionary Learning for Person Re-identification
TLDR
Two coupled dictionaries that relate to the gallery and probe cameras are jointly learned in the training phase from both labeled and unlabeled images, and experimental results on publicly available datasets demonstrate the superiority of this method. Expand
Learning to rank in person re-identification with metric ensembles
TLDR
This work proposes an effective structured learning based approach to the problem of person re-identification which outperforms the current state-of-the-art on most benchmark data sets evaluated and formulates two optimization algorithms, which directly optimize evaluation measures commonly used in person re -identification. Expand
Relaxed Pairwise Learned Metric for Person Re-identification
TLDR
This paper proposes to learn a metric from pairs of samples from different cameras, so that even less sophisticated features describing color and texture information are sufficient for finally getting state-of-the-art classification results. Expand
Person re-identification by Local Maximal Occurrence representation and metric learning
  • Shengcai Liao, Yang Hu, Xiangyu Zhu, S. Li
  • Computer Science, Mathematics
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
This paper proposes an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA), and presents a practical computation method for XQDA. Expand
Dictionary Learning with Iterative Laplacian Regularisation for Unsupervised Person Re-identification
TLDR
A new dictionary learning for sparse coding formulation with a graph Laplacian regularisation term whose value is set iteratively enables the exploitation of cross-view identity-discriminative information ignored by existing unsupervised Re-ID methods. Expand
Person Re-Identification by Iterative Re-Weighted Sparse Ranking
TLDR
The approach makes use of soft- and hard- re-weighting to redistribute energy among the most relevant contributing elements and to ensure that the best candidates are ranked at each iteration of an iterative extension to sparse discriminative classifiers capable of ranking many candidate targets. Expand
Unsupervised Salience Learning for Person Re-identification
TLDR
A novel perspective for person re-identification based on unsupervised salience learning, which applies adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations. Expand
...
1
2
3
4
5
...