Enhancing Person Re-identification in a Self-Trained Subspace

By Xun Yang, Meng Wang, Richang Hong, Qi Tian, Yong Rui. 2017

86 citations recorded by the source corpus.

Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety of algorithms have been developed in the fully supervised setting, requiring access to a large amount of labeled training data. However, the main bottleneck for fully supervised re-ID is the limited availability of labeled training samples. To address this problem, we propose a self-trained subspace learning paradigm for person re-ID that effectively utilizes both labeled and unlabeled data to learn a discriminative subspace where person images across disjoint camera views can be easily matched. The proposed approach first constructs pseudo-pairwise relationships among unlabeled persons using the k-nearest neighbors algorithm. Then, with the pseudo-pairwise relationships, the unlabeled samples can be easily combined with the labeled samples to learn a discriminative projection by solving an eigenvalue problem. In addition, we refine the pseudo-pairwise relationships iteratively, which further improves learning performance. A multi-kernel embedding strategy is also incorporated into the proposed approach to cope with the non-linearity in a person’s appearance and explore the complementation of multiple kernels. In this way, the performance of person re-ID can be greatly enhanced when training data are insufficient. Experimental results on six widely used datasets demonstrate the effectiveness of our approach, and its performance can be comparable to the reported results of most state-of-the-art fully supervised methods while using much fewer labeled data.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tat-seng Chua
2. Xiangnan He
3. Dacheng Tao
4. Yueting Zhuang
5. Zhou Zhao
6. Hanwang Zhang
7. Jun Xiao
8. Tongliang Liu

In Biomedical Engineering

1. Yi Yang
2. Zhedong Zheng
3. Liang Zheng
4. Dacheng Tao
5. Yueting Zhuang
6. Jun Xiao
7. Mingming Gong
8. Xinmei Tian

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yi Yang
3. Cordelia Schmid
4. Luc Van Gool
5. Liang Zheng
6. Hanwang Zhang
7. Xiaogang Wang
8. Tat-seng Chua

Citations in the corpus

• Domain Generalization via Conditional Invariant Representations (2018, background): “There are also other examples, e.g. speaker recognition and person re-identification (Yang et al. 2017).”
• A Discriminatively Learned CNN Embedding for Person Reidentification (2016, methodology): “[45] use Gaussian of Gaussian feature [23] to conduct semisupervised learning.”
• Video Question Answering via Gradually Refined Attention over Appearance and Motion (2017, background): “Video question answering (VideoQA) can help us quickly acquire the necessary information we seek from videos, which is beneficial to various real-life applications [4, 8, 28, 29, 36].”
• Pedestrian Alignment Network for Large-scale Person Re-Identification (2017, methodology): “use Gaussian of Gaussian feature [24] to conduct semi-supervised learning [25].”