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 resourceconstrained 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.

CDTNet: Improved Image Classification Method Using Standard, Dilated and Transposed Convolutions

“…At the same time, we also compared the parameters of these models. The parameters can be calculated as Formula (6) [21]:…”

“…Feature fusion is an important operation in the CNN models, which can transmit the information of lower layers directly to higher layers [21]. Merging the features from different layers can achieve the effect of aggregating information from different RFs.…”

“…The excellent performance of CNNs comes from their wider and deeper models [4]; however, these models have also faced an increasing memory burden [21], which limits their application in resource-constrained and high real-time requirement scenarios, such as mobile terminals and embedded systems with low hardware resources [22,23].…”

Product Re-identification System in Fully Automated Defect Detection

“…Zhou et ai. [41] proposed to combine different granularity features from the block1, block2, block3, block4, and block5 in VGG to construct a new network architecture. A local fully connected layer was added after each block to reduce the dimensionality of the features.…”

Effects of Explosive Strength Training on Lower Limbs in Taekwondo Athletes

“…3 Zhou Y mentioned that the essence of human motion needs to be understood from the perspective of action and energy metabolism, and different action patterns are formed on the basis of the co-contraction of agonist and synergistic muscles. 4 In general, the athletic ability exhibited by different sports varies, Taekwondo is a sport that requires a mixture of aerobic and anaerobic intermittent ability, rapid bursts and high agility. Therefore, under the existing physical fitness characteristic model and grade evaluation standard, it has become an important task to effectively connect the physical fitness of Taekwondo with the special training ability in combination with a scientific training plan.…”