Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification

@article{Wu2017DeepLD,
  title={Deep Linear Discriminant Analysis on Fisher Networks: A Hybrid Architecture for Person Re-identification},
  author={Lin Wu and Chunhua Shen and Anton van den Hengel},
  journal={ArXiv},
  year={2017},
  volume={abs/1606.01595}
}

Figures and Tables from this paper

Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
Person Re-Identification Using Hybrid Representation Reinforced by Metric Learning
TLDR
The experimental results show that the hybrid hand-crafted and deep features outperformed the existing state-of-the-art in approaches in the unsupervised paradigm.
A Multi-loss Deep Network Based on Pyramid Pooling for Person Re-identification
TLDR
A multi-loss siamese network with pyramid pooling structure for person re-ID that can get a better discriminative representation and achieve a better performance on two large public datasets including Market1501 and CUHK03.
Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
TLDR
A Feature Mask Network (FMN) is proposed that takes advantage of ResNet high-level features to predict a feature map mask and then imposes it on the low- level features to dynamically reweight different object parts for a locally aware feature representation.
Cross-Entropy Adversarial View Adaptation for Person Re-Identification
TLDR
This work learns view-invariant subspace for person re-ID, and its corresponding similarity metric using an adversarial view adaptation approach, and achieves notably improved performance in comparison with the state-of-the-arts on benchmark datasets.
Cross-View Discriminative Feature Learning for Person Re-Identification
TLDR
This technique, by dismissing side-sources of performance gain, proves to enhance the CNN invariance to viewpoint without incurring increased training complexity and outperforms many related state-of-the-art techniques on Market-1501 and CUHK03.
A Discriminatively Learned CNN Embedding for Person Reidentification
TLDR
This article proposes a Siamese network that simultaneously computes the identification loss and verification loss and learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations.
Person Re-Identification Based on Heterogeneous Part-Based Deep Network in Camera Networks
TLDR
A new deep learning model named heterogeneous part-based deep network for person re-identification in camera networks, which simultaneously learns the alignment and discrimination for parts of pedestrian images, outperforming the state-of-the-art methods by a large margin.
...
...

References

SHOWING 1-10 OF 72 REFERENCES
Learning a Discriminative Null Space for Person Re-identification
  • Li ZhangT. XiangS. Gong
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This work proposes to overcome the SSS problem in re-id distance metric learning by matching people in a discriminative null space of the training data, which has a fixed dimension, a closed-form solution and is very efficient to compute.
An improved deep learning architecture for person re-identification
TLDR
This work presents a deep convolutional architecture with layers specially designed to address the problem of re-identification, and significantly outperforms the state of the art on both a large data set and a medium-sized data set, and is resistant to over-fitting.
PersonNet: Person Re-identification with Deep Convolutional Neural Networks
TLDR
A deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification and an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into this architecture, which is beneficial to deep nets.
Deep Ranking for Person Re-Identification via Joint Representation Learning
TLDR
A novel approach to person re-identification, a fundamental task in distributed multi-camera surveillance systems, is proposed that significantly outperforms all the state-of-the-art approaches, including both traditional and CNN-based methods on the challenging VIPeR, CUHK-01, and CAVIAR4REID datasets.
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.
Deep Metric Learning for Person Re-identification
TLDR
A more general way that can learn a similarity metric from image pixels directly by using a "siamese" deep neural network that can jointly learn the color feature, texture feature and metric in a unified framework is proposed.
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.
Feature Extraction With Deep Neural Networks by a Generalized Discriminant Analysis
TLDR
The generalized discriminant analysis (GerDA) proposed in this paper uses nonlinear transformations that are learnt by DNNs in a semisupervised fashion and displays excellent performance on real-world recognition and detection tasks, such as handwritten digit recognition and face detection.
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.
Person Re-identification by Efficient Impostor-Based Metric Learning
TLDR
This paper addresses the first problem by learning the transition from one camera to the other by learning a Mahalanobis metric using pairs of labeled samples from different cameras, which additionally provides much better generalization properties.
...
...