Image
Image
Image
Image
Image
Image
Image
Image
Image
Image



Search
»

mcKLR & mckNN

Description: This package includes two approaches to multi-class cost-sensitive learning, that is, mcKLR and mckNN. The description of mcKLR can be found in our TPAMI paper and CVPR'08 paper; the description of mckNN can be found in our TPAMI paper. Both approaches have been applied to face recognition with success. In these papers we argue that face recognition is inherently a task involving unequal misclassification costs, and therefore we should try to minimize the costs instead of minimizing the number of mistakes, yet almost all previous face recognition research focus only on minimizing the number of mistakes! The mcKLR and mckNN approaches, however, can also be applied to other tasks which involve multi-class cost-sensitive learning.

References:

Y. Zhang and Z.-H. Zhou. Cost-sensitive face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, in press. (Early version at CVPR'08)

ATTN: This package is free for academic usage. You can run it at your own risk. For other purposes, please contact .

Requirement: The package was developed with MATLAB. The Java routines can be called in MATLAB environment.

ATTN2: This package was developed by . For any problem concerning the code, please feel free to contact Mr. Zhang.

Download: [code] (9Kb)
  Name Size
- mcKLR_mckNN.rar 8.38 KB

Image
PoweredBy © LAMDA, 2022