Name
Abstract | ||
|---|---|---|
This paper proposes an algorithm, particularly a loss function and its end to end learning manner, for person re-identification task. The main idea is to take full advantage of the labels in a batch during training, and to employ PCA to extract discriminative features. Deriving from the classic eigenvalue computation problem in PCA, our method incorporates an extra term in loss function with the purpose of minimizing those relative large eigenvalues. And the derivative with respect to the designed loss can be back-propagated in deep network by stochastic gradient descent (SGD). Experiments show the effectiveness of our algorithm on several re-id datasets. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1007/978-3-319-73600-6_18 | Lecture Notes in Computer Science |
Field | DocType | Volume |
Stochastic gradient descent,Pattern recognition,Computer science,End-to-end principle,Eigenvalue computation,Artificial intelligence,Discriminative model,Eigenvalues and eigenvectors | Conference | 10705 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
20 | 5 | |