Quadratic mutual information regularization in real-time deep CNN models
This work addresses the need for efficient and generalizable models in autonomous systems, but it appears incremental as it builds on existing lightweight CNN approaches with a new regularization technique.
The paper tackled the problem of real-time deep CNN models for high-resolution video on devices with limited computational power, proposing a Quadratic Mutual Information regularization method to improve generalization, with experiments on binary classification in autonomous systems showing effectiveness.
In this paper, regularized lightweight deep convolutional neural network models, capable of effectively operating in real-time on devices with restricted computational power for high-resolution video input are proposed. Furthermore, a novel regularization method motivated by the Quadratic Mutual Information, in order to improve the generalization ability of the utilized models is proposed. Extensive experiments on various binary classification problems involved in autonomous systems are performed, indicating the effectiveness of the proposed models as well as of the proposed regularizer.