A feature learning approach for face recognition with robustness to noisy label based on top- prediction

Neurocomputing, pp. 48-55, 2019.

Cited by: 3|Bibtex|Views3|DOI:https://doi.org/10.1016/j.neucom.2018.10.075
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|www.sciencedirect.com

Abstract:

Collecting a vast amount of face data with identity labels to train a convolutional neural network is an effective mean to learn a discriminative feature representation for face recognition. However, the datasets with larger scale often contain more noisy labels, that directly affects the ultimate performance of the learned model. This pa...More

Code:

Data:

Your rating :
0

 

Tags
Comments