Open AccessAnalysis of the latent space of pre-trained deep convolutional neural networks in the problem of automatic segmentation of color images
Author(s) -
В. А. Галкин,
Alexei Makarenko,
D. Targamadze
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1925/1/012048
Subject(s) - autoencoder , artificial intelligence , pattern recognition (psychology) , segmentation , computer science , convolutional neural network , artificial neural network , color space , space (punctuation) , deep learning , computer vision , image (mathematics) , operating system
The paper presents a primary study of the latent space structure of neural networks trained for semantic segmentation. Segmentation was performed in a controlled environment of three classes of colored rectangular shapes. The classic autoencoder and U-net like architectures were chosen as reference architectures. To study the structure of the space, a combination of a perceptron that linearly separates classes and the compression algorithms UMAP and PCA was used. As a result, a tool was obtained for evaluating the quality of a neural network based on the degree of separability of classes in the latent space of the network.