Unsupervised feature learning with C-SVDDNet

作者：

Highlights：

• A single layer network—CSVDDNet is proposed for unsupervised feature learning.

• Unsupervised feature learning methods can be useful when training set is small.

• Networks with different receptive field can be combined to make a better prediction.

• SIFT representation can be used in unsupervised feature learning network.

摘要

Highlights•A single layer network—CSVDDNet is proposed for unsupervised feature learning.•Unsupervised feature learning methods can be useful when training set is small.•Networks with different receptive field can be combined to make a better prediction.•SIFT representation can be used in unsupervised feature learning network.

论文关键词：Unsupervised feature learning,K-means,Support Vector Data Description (SVDD),Centering SVDD (C-SVDD),C-SVDDNet

论文评审过程：Received 27 January 2016, Revised 30 April 2016, Accepted 1 June 2016, Available online 4 June 2016, Version of Record 21 June 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.06.001