Abstract | ||
---|---|---|
We propose a highly structured neural network architecture for semantic segmentation with an extremely small model size, suitable for low-power embedded and mobile platforms. Specifically, our architecture combines i) a Haar wavelet-based tree-like convolutional neural network (CNN), ii) a random layer realizing a radial basis function kernel approximation, and iii) a linear classifier. While stages i) and ii) are completely pre-specified, only the linear classifier is learned from data. We apply the proposed architecture to outdoor scene and aerial image semantic segmentation and show that the accuracy of our architecture is competitive with conventional pixel classification CNNs. Furthermore, we demonstrate that the proposed architecture is data efficient in the sense of matching the accuracy of pixel classification CNNs when trained on a much smaller data set. |
Year | DOI | Venue |
---|---|---|
2017 | 10.23919/EUSIPCO.2017.8081169 | 2017 25th European Signal Processing Conference (EUSIPCO) |
Keywords | DocType | Volume |
deep structured features,highly structured neural network architecture,Haar wavelet,tree-like convolutional neural network,random layer,radial basis function kernel approximation,linear classifier,aerial image semantic segmentation,conventional pixel classification CNNs,outdoor scene,CNN | Conference | abs/1609.07916 |
ISSN | ISBN | Citations |
2076-1465 | 978-1-5386-0751-0 | 4 |
PageRank | References | Authors |
0.49 | 17 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Tschannen | 1 | 143 | 13.58 |
Cavigelli, L. | 2 | 244 | 22.75 |
Fabian Mentzer | 3 | 60 | 5.08 |
Thomas Wiatowski | 4 | 19 | 2.38 |
Luca Benini | 5 | 13116 | 1188.49 |