Sergey A. Ilyuhin,1,2 Alexander Sheshkus,1,3 Vladimir Arlazarov3,2
1Smart Engines Service LLC (Russian Federation) 2Moscow Institute of Physics and Technology (Russian Federation) 3Federal Research Ctr. "Computer Science and Control" of RAS (Russian Federation)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Image recognition includes problems where special features can be found only in a specific area of an image. This fact suggests us to apply different filters to different areas of input images. Convolutional networks have only fully-connected and locally-connected layers to make it. A Fully-connected layer erases the position factor for every output and a locally connected layer storage an enormous number of parameters. We need a layer that can apply different convolution kernels for different areas of an input image and not carry so many parameters as a locally-connected layer for high scale resolution images. This is why in this paper, we introduce a new type of convolutional layer - a block layer, and a way to construct a neural network using block convolutional layers to achieve better performance in the image classification problem. The influence of block layers on the quality of the neural network classifier is shown in this paper. We also provide a comparison with neural network architecture LeNet-5 as a baseline. The research was conducted on open datasets: MNIST, CIFAR-10, Fashion MNIST. The results of our research prove that this layer can increase the accuracy of neural network classifiers without increasing the number of operations for the neural network.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Sergey A. Ilyuhin, Alexander Sheshkus, Vladimir Arlazarov, "Block convolutional layer for position dependent features calculation," Proc. SPIE 11605, Thirteenth International Conference on Machine Vision, 116050R (4 January 2021); https://doi.org/10.1117/12.2587458