Abstract
Abstract. In this paper we propose a new technic called etalons, which allows us to interpret the way how convolution network makes its predictions. This mechanism is very similar to voting among different experts. Thereby CNN could be interpreted as a variety of experts, but it acts not like a sum or product of them, but rather represent a complicated hierarchy. We implement algorithm for etalon acquisition based on well-known properties of affine maps. We show that neural net has two high-level mechanisms of voting: first, based on attention to input image regions, specific to current input, and second, based on ignoring specific input regions. We also make an assumption that there is a connection between complexity of the underlying data manifold and the number of etalon images and their quality.
Highlights
For the last past years in computer vision society there were introduced tremendous variety of different neural networks architectures (Redmon et al, 2016), (Girshick, 2015), (He et al, 2016)
We don’t consider the problem of representation capability, we suppose that there is a connection between complexity of the underlying data manifold and the number of etalon images and their quality
In this work we represent a new notion – etalon images, which are defined as affine maps for any neuron and given input image
Summary
For the last past years in computer vision society there were introduced tremendous variety of different neural networks architectures (Redmon et al, 2016), (Girshick, 2015), (He et al, 2016). There are different ideas behind these nets, which are explained by intuition and a good guess rather than strict theory, but the core blocks all of them are the same – they all utilize convolution and pooling layers Such first CNNs as AlexNet and VGG, using only simple convolutions and pooling blocks without any additional connections (that exist in ResNet and DenseNet), haven’t shown such good quality, compared to the modern CNN architectures. They have demonstrated the ability to fit data and to outperform previous state of the art algorithms. As known CNN gives effective implicit representation of this manifold and etalons give way to look at it
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
