In recent years, deep convolutional neural network (CNN) has been applied more and more increasingly used in computer vision, natural language processing and other fields. At the same time, low-power platforms have more and more significant requirements for the size of the network. This paper proposed CED-Net (Channel enhancement DenseNet), a more efficient densely connected network. It combined the bottleneck layer with learned group convolution and channel enhancement module. The bottleneck layer with learned group convolution could effectively increase the network's accuracy without too many extra parameters and computation (FLOPs, Floating Point Operations). The channel enhancement module improved the representation of the network by increasing the interdependency between convolutional feature channels. CED-Net is designed regarding CondenseNet's structure, and our experiments show that the CED-Net is more effective than CondenseNet and other advanced lightweight CNNs. Accuracy on the CIFAR-10 dataset and CIFAR-100 dataset is 0.4 and 1% higher than that on CondenseNet, respectively, but they have almost the same number of parameters and FLOPs. Finally, the ablation experiment proves the effectiveness of the bottleneck layer used in CED-Net.
Keywords: CondenseNet; Squeeze and Excitation; bottleneck layer; channel enhancement; convolutional neural network.