Hierarchical learning of sparse image representations using steered mixture-of-experts
- Author
- R. Jongebloed, Ruben Verhack, L. Lange and T. Sikora
- Organization
- Abstract
- Previous research showed highly efficient compression results for low bit-rates using Steered Mixture-of-Experts (SMoE), higher rates still pose a challenge due to the non-convex optimization problem that becomes more difficult when increasing the number of components. Therefore, a novel estimation method based on Hidden Markov Random Fields is introduced taking spatial dependencies of neighboring pixels into account combined with a tree-structured splitting strategy. Experimental evaluations for images show that our approach outperforms state-of-the-art techniques using only one robust parameter set. For video and light field modeling even more gain can be expected.
- Keywords
- Steered Mixture-of-Experts, Sparse Representation, Hidden Markov Random Field, Denoising, Image Signal Processing, Inference
Downloads
-
(...).pdf
- full text
- |
- UGent only
- |
- |
- 937.19 KB
-
DS176 i.pdf
- full text
- |
- open access
- |
- |
- 940.69 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8578336
- MLA
- Jongebloed, R., et al. “Hierarchical Learning of Sparse Image Representations Using Steered Mixture-of-Experts.” 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018), 2018, doi:10.1109/ICMEW.2018.8551561.
- APA
- Jongebloed, R., Verhack, R., Lange, L., & Sikora, T. (2018). Hierarchical learning of sparse image representations using steered mixture-of-experts. 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018). Presented at the IEEE International Conference on Multimedia and Expo (ICMEW), San Diego, USA. https://doi.org/10.1109/ICMEW.2018.8551561
- Chicago author-date
- Jongebloed, R., Ruben Verhack, L. Lange, and T. Sikora. 2018. “Hierarchical Learning of Sparse Image Representations Using Steered Mixture-of-Experts.” In 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018). https://doi.org/10.1109/ICMEW.2018.8551561.
- Chicago author-date (all authors)
- Jongebloed, R., Ruben Verhack, L. Lange, and T. Sikora. 2018. “Hierarchical Learning of Sparse Image Representations Using Steered Mixture-of-Experts.” In 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018). doi:10.1109/ICMEW.2018.8551561.
- Vancouver
- 1.Jongebloed R, Verhack R, Lange L, Sikora T. Hierarchical learning of sparse image representations using steered mixture-of-experts. In: 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018). 2018.
- IEEE
- [1]R. Jongebloed, R. Verhack, L. Lange, and T. Sikora, “Hierarchical learning of sparse image representations using steered mixture-of-experts,” in 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018), San Diego, USA, 2018.
@inproceedings{8578336,
abstract = {{Previous research showed highly efficient compression results for low bit-rates using Steered Mixture-of-Experts (SMoE), higher rates still pose a challenge due to the non-convex optimization problem that becomes more difficult when increasing the number of components. Therefore, a novel estimation method based on Hidden Markov Random Fields is introduced taking spatial dependencies of neighboring pixels into account combined with a tree-structured splitting strategy. Experimental evaluations for images show that our approach outperforms state-of-the-art techniques using only one robust parameter set. For video and light field modeling even more gain can be expected.}},
articleno = {{8551561}},
author = {{Jongebloed, R. and Verhack, Ruben and Lange, L. and Sikora, T.}},
booktitle = {{2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018)}},
isbn = {{9781538641958}},
issn = {{2330-7927}},
keywords = {{Steered Mixture-of-Experts,Sparse Representation,Hidden Markov Random Field,Denoising,Image Signal Processing,Inference}},
language = {{eng}},
location = {{San Diego, USA}},
pages = {{6}},
title = {{Hierarchical learning of sparse image representations using steered mixture-of-experts}},
url = {{http://doi.org/10.1109/ICMEW.2018.8551561}},
year = {{2018}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: