A Novel lightweight Convolutional Neural Network, ExquisiteNetV2

TL;DR

ExquisiteNetV2 is a new lightweight CNN that outperforms its predecessor and other models in accuracy, speed, and parameter efficiency across multiple datasets.

Contribution

The paper introduces ExquisiteNetV2, a faster, more accurate, and parameter-efficient CNN model that surpasses previous versions and well-known models in classification tasks.

Findings

ExquisiteNetV2 achieves the highest accuracy on over half of the datasets.

It has the fewest parameters among compared models.

It demonstrates faster computation speed in most cases.

Abstract

In the paper of ExquisiteNetV1, the ability of classification of ExquisiteNetV1 is worse than DenseNet. In this article, we propose a faster and better model ExquisiteNetV2. We conduct many experiments to evaluate its performance. We test ExquisiteNetV2, ExquisiteNetV1 and other 9 well-known models on 15 credible datasets under the same condition. According to the experimental results, ExquisiteNetV2 gets the highest classification accuracy over half of the datasets. Important of all, ExquisiteNetV2 has fewest amounts of parameters. Besides, in most instances, ExquisiteNetV2 has fastest computing speed.