A concatenating framework of shortcut convolutional neural networks
This work addresses performance and stability issues in image classification and recognition tasks, but it is incremental as it builds on existing shortcut connection methods.
The authors tackled the limitation of traditional convolutional neural networks in integrating multi-scale information by proposing a concatenating framework with shortcut connections to the fully-connected layer, achieving better results and more stability across various benchmark datasets and settings.
It is well accepted that convolutional neural networks play an important role in learning excellent features for image classification and recognition. However, in tradition they only allow adjacent layers connected, limiting integration of multi-scale information. To further improve their performance, we present a concatenating framework of shortcut convolutional neural networks. This framework can concatenate multi-scale features by shortcut connections to the fully-connected layer that is directly fed to the output layer. We do a large number of experiments to investigate performance of the shortcut convolutional neural networks on many benchmark visual datasets for different tasks. The datasets include AR, FERET, FaceScrub, CelebA for gender classification, CUReT for texture classification, MNIST for digit recognition, and CIFAR-10 for object recognition. Experimental results show that the shortcut convolutional neural networks can achieve better results than the traditional ones on these tasks, with more stability in different settings of pooling schemes, activation functions, optimizations, initializations, kernel numbers and kernel sizes.