%0 Conference Paper %1 monti_geometric_2017 %A Monti, Federico %A Boscaini, Davide %A Masci, Jonathan %A Rodola, Emanuele %A Svoboda, Jan %A Bronstein, Michael M. %B 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) %C Honolulu, HI %D 2017 %I IEEE %K imported %P 5425--5434 %R 10.1109/CVPR.2017.576 %T Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs %U http://ieeexplore.ieee.org/document/8100059/ %X Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural language processing, and computer vision. In particular, convolutional neural network (CNN) architectures currently produce state-of-the-art performance on a variety of image analysis tasks such as object detection and recognition. Most of deep learning research has so far focused on dealing with 1D, 2D, or 3D Euclideanstructured data such as acoustic signals, images, or videos. Recently, there has been an increasing interest in geometric deep learning, attempting to generalize deep learning methods to non-Euclidean structured data such as graphs and manifolds, with a variety of applications from the domains of network analysis, computational social science, or computer graphics. In this paper, we propose a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features. We show that various non-Euclidean CNN methods previously proposed in the literature can be considered as particular instances of our framework. We test the proposed method on standard tasks from the realms of image-, graphand 3D shape analysis and show that it consistently outperforms previous approaches. %@ 978-1-5386-0457-1

@inproceedings{monti_geometric_2017, abstract = {Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural language processing, and computer vision. In particular, convolutional neural network (CNN) architectures currently produce state-of-the-art performance on a variety of image analysis tasks such as object detection and recognition. Most of deep learning research has so far focused on dealing with 1D, 2D, or 3D Euclideanstructured data such as acoustic signals, images, or videos. Recently, there has been an increasing interest in geometric deep learning, attempting to generalize deep learning methods to non-Euclidean structured data such as graphs and manifolds, with a variety of applications from the domains of network analysis, computational social science, or computer graphics. In this paper, we propose a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features. We show that various non-Euclidean CNN methods previously proposed in the literature can be considered as particular instances of our framework. We test the proposed method on standard tasks from the realms of image-, graphand 3D shape analysis and show that it consistently outperforms previous approaches.}, added-at = {2020-02-21T16:09:44.000+0100}, address = {Honolulu, HI}, author = {Monti, Federico and Boscaini, Davide and Masci, Jonathan and Rodola, Emanuele and Svoboda, Jan and Bronstein, Michael M.}, biburl = {https://www.bibsonomy.org/bibtex/2b2cf3d62adcfeda8696d6c11f6531c3c/tschumacher}, booktitle = {2017 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition} ({CVPR})}, doi = {10.1109/CVPR.2017.576}, file = {Monti et al - Geometric deep learning on graphs and manifolds using mixture model CNNs.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Monti et al - Geometric deep learning on graphs and manifolds using mixture model CNNs.pdf:application/pdf}, interhash = {bc56578e5f0bf8fb494888967d7a260b}, intrahash = {b2cf3d62adcfeda8696d6c11f6531c3c}, isbn = {978-1-5386-0457-1}, keywords = {imported}, language = {en}, month = jul, pages = {5425--5434}, publisher = {IEEE}, timestamp = {2020-02-21T16:09:44.000+0100}, title = {Geometric {Deep} {Learning} on {Graphs} and {Manifolds} {Using} {Mixture} {Model} {CNNs}}, url = {http://ieeexplore.ieee.org/document/8100059/}, urldate = {2020-02-02}, year = 2017 }