A Novel lightweight Convolutional Neural Network, ExquisiteNetV2
arXiv:2105.09008
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.
arXiv comment6 pages, 6 figures, 29 tables
References in corpus (7)
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Densely Connected Convolutional Networks
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- A Public Image Database for Benchmark of Plant Seedling Classification Algorithms
- GhostNet: More Features from Cheap Operations
- Effects of Degradations on Deep Neural Network Architectures
- Gradient Centralization: A New Optimization Technique for Deep Neural Networks