Improving the performance of lightweight CNNs for binary classification using quadratic mutual information regularization

作者：

Highlights：

• We propose regularized lightweight deep CNN models for various classification problems, capable of running in realtime ondrone.

• We empirically study the impact of hinge loss against cross entropy loss in binary classification problems and we argue that the hinge loss is better for binary classification problems.

• We propose a novel regularizer based on the Quadratic Mutual Information criterion in order to enhance the generalization ability of the proposed models.

摘要

•We propose regularized lightweight deep CNN models for various classification problems, capable of running in realtime ondrone.•We empirically study the impact of hinge loss against cross entropy loss in binary classification problems and we argue that the hinge loss is better for binary classification problems.•We propose a novel regularizer based on the Quadratic Mutual Information criterion in order to enhance the generalization ability of the proposed models.

论文关键词：Hinge loss,Cross entropy loss,Binary classification problems,Quadratic mutual information,Regularizer,Lightweight models,Real-time,Convolutional neural networks,Deep learning

论文评审过程：Received 22 December 2018, Revised 20 February 2020, Accepted 28 April 2020, Available online 16 May 2020, Version of Record 21 May 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107407