ETALON IMAGES: UNDERSTANDING THE CONVOLUTION NEURAL NETWORKS
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...
Main Authors: | V. V. Molchanov, B. V. Vishnyakov, V. S. Gorbatsevich, Y. V. Vizilter |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2018-05-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2/707/2018/isprs-archives-XLII-2-707-2018.pdf |
Similar Items
-
Structure-functional analysis and synthesis of deep convolutional neural networks
by: Yuri Vizilter, et al.
Published: (2019-10-01) -
USING MORPHLET-BASED IMAGE REPRESENTATION FOR OBJECT DETECTION
by: V. S. Gorbatsevich, et al.
Published: (2016-06-01) -
FaceDetectNet: face detection via fully-convolutional network
by: Vladimir Gorbatsevich, et al.
Published: (2019-02-01) -
Fast Moving Objects Detection Using iLBP Background Model
by: B. Vishnyakov, et al.
Published: (2014-08-01) -
Automatic Image Colorization Based on Convolutional Neural Networks
by: L. V. Serebryanaya, et al.
Published: (2020-07-01)