Kernelised reference‐wise metric learning
Unlike the doublet or triplet constraints, a novel kernelised reference‐wise metric learning is proposed by constructing reference‐wise constraints, which contain similarity information of each sample to all reference samples. After selecting several representative training samples as the reference...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-03-01
|
| Series: | Electronics Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/el.2016.4079 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Unlike the doublet or triplet constraints, a novel kernelised reference‐wise metric learning is proposed by constructing reference‐wise constraints, which contain similarity information of each sample to all reference samples. After selecting several representative training samples as the reference set, the training data are first mapped into a projected space by the reference sample matrix. Then the problem of metric learning is casted as a multi‐label classification problem under the reference‐wise constraints, in which an l2‐norm regularised least squares canonical correlation analysis can be used. Besides, the formulation is generalised to kernelised version for further boosting the performance. Experiments on two benchmark person re‐identification datasets demonstrate that the approach clearly outperforms the state‐of‐the‐art methods. |
|---|---|
| ISSN: | 0013-5194 1350-911X |