Improving classification with semi-supervised and fine-grained learning

作者：

Highlights：

• We propose the Improved Pseudo-Label for semi-supervised learning.

• We propose a new method for fine-grained feature learning.

• Our model can be applied to domain adaptation quickly and effectively.

• Our approach can combine almost all deep neural network models and training methods.

• Extensive experiments on two challenging datasets demonstrate the effectiveness of our approach.

摘要

•We propose the Improved Pseudo-Label for semi-supervised learning.•We propose a new method for fine-grained feature learning.•Our model can be applied to domain adaptation quickly and effectively.•Our approach can combine almost all deep neural network models and training methods.•Extensive experiments on two challenging datasets demonstrate the effectiveness of our approach.

论文关键词：Semi-supervised learning,Fine-grained feature learning,Mixture of DCNNs,Image classification

论文评审过程：Received 26 March 2018, Revised 29 September 2018, Accepted 6 December 2018, Available online 7 December 2018, Version of Record 21 December 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.12.002