Improving the Performance of VGG Through Different Granularity Feature Combinations

Abstract

Convolutional neural networks have achieved amazing success in many areas in recent years, and VGG is a widely used convolutional neural network model. However, it has some limitations, such as a large number of parameters, which take up significant memory and thus restrict its application in resource-constrained scenarios such as mobile devices and embedded systems. In convolutional neural network models, the different number of convolutional layers can extract different granularity features, which represent the different levels of importance in the image recognition process. Here, we propose a new VGG architecture with different granularity feature combinations that combine different granularity features from block1, block2, block3, block4, and block5 in VGG. Each block is followed by a local fully connected layer to reduce the dimensionality of the coarse and fine features, and five different granularity features are combined as the input of the first global fully connected layer. By combining the features of different blocks, it can increase information flow from a lower layer directly to a fully connected layer and increase feature reuse without adding too many connections. The addition of five local fully connected layers means an increase in parameters, so we reduce the neuron number in two global fully connected layers to reduce the number of parameters. The well-known datasets CIFAR-10 and MNIST were used to evaluate the network's classification performance. The experimental results show that the proposed model achieves better training and testing performance than traditional VGGs and reduces the number of parameters.

Keywords

• Combination
• convergence speed
• different granularity
• feature
• performance