Neural Bag-of-Features learning

作者：

Highlights：

• A neural generalization of the Bag-of-Features (BoF) model is introduced.

• The proposed model supports the discriminant weighting of the feature space.

• Two incremental algorithms (for training and classification) are proposed.

• A method for providing visual attention information for the BoF model is introduced.

• The proposed method is evaluated using four datasets from different domains.

摘要

Highlights•A neural generalization of the Bag-of-Features (BoF) model is introduced.•The proposed model supports the discriminant weighting of the feature space.•Two incremental algorithms (for training and classification) are proposed.•A method for providing visual attention information for the BoF model is introduced.•The proposed method is evaluated using four datasets from different domains.

论文关键词：Bag-of-Features,RBF neural networks,Dictionary learning

论文评审过程：Received 23 March 2016, Revised 18 August 2016, Accepted 16 November 2016, Available online 21 November 2016, Version of Record 30 November 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.11.014