Paper Info
Title
Isometric Transformation Invariant Graph-based Deep Neural Network.
Abstract
Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have achieved only limited success in the classification of images that undergo geometric transformations. In this work we present a novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images. In particular, images are represented as signals on graphs, which permits to replace classical convolution and pooling layers in deep networks with graph spectral convolution and dynamic graph pooling layers that together contribute to invariance to isometric transformation. Our experiments show high performance on rotated and translated images from the test set compared to classical architectures that are very sensitive to transformations in the data. The inherent invariance properties of our framework provide key advantages, such as increased resiliency to data variability and sustained performance with limited training sets. Our code is available online.
Year
Venue
Field
2018
arXiv: Computer Vision and Pattern Recognition
Pattern recognition,Invariant (physics),Convolution,Computer science,Transformation geometry,Pooling,Invariant (mathematics),Artificial intelligence,Artificial neural network,Isometric exercise,Test set
DocType
Volume
Citations 
Journal
abs/1808.07366
1
PageRank 
References 
Authors
0.35
11
2
Name
Order
Citations
PageRank
Renata Khasanova1142.44
Pascal Frossard23015230.41