Deep feature learning via structured graph Laplacian embedding for person re-identification
- Publisher:
- ELSEVIER SCI LTD
- Publication Type:
- Journal Article
- Citation:
- Pattern Recognition, 2018, 82, pp. 94-104
- Issue Date:
- 2018-10-01
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 1-s2.0-S0031320318301717-main.pdf | Published version | 1.34 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Learning the distance metric between pairs of examples is of great importance for visual recognition, especially for person re-identification (Re-Id). Recently, the contrastive and triplet loss are proposed to enhance the discriminative power of the deeply learned features, and have achieved remarkable success. As can be seen, either the contrastive or triplet loss is just one special case of the Euclidean distance relationships among these training samples. Therefore, we propose a structured graph Laplacian embedding algorithm, which can formulate all these structured distance relationships into the graph Laplacian form. The proposed method can take full advantages of the structured distance relationships among these training samples, with the constructed complete graph. Besides, this formulation makes our method easy-to-implement and super-effective. When embedding the proposed algorithm with the softmax loss for the CNN training, our method can obtain much more robust and discriminative deep features with inter-personal dispersion and intra-personal compactness, which is essential to person Re-Id. We did experiments on top of three popular networks, namely AlexNet [1], DGDNet [2] and ResNet50 [3], on recent four widely used Re-Id benchmark datasets, and it shows that the proposed structure graph Laplacian embedding is very effective.
Please use this identifier to cite or link to this item: