Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY 14623, USA
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(24), 5361; https://doi.org/10.3390/s19245361
Received: 25 October 2019 / Revised: 20 November 2019 / Accepted: 29 November 2019 / Published: 5 December 2019
(This article belongs to the Special Issue Advanced Computational Intelligence for Object Detection, Feature Extraction and Recognition in Smart Sensor Environments)
We propose a new efficient architecture for semantic segmentation, based on a “Waterfall” Atrous Spatial Pooling architecture, that achieves a considerable accuracy increase while decreasing the number of network parameters and memory footprint. The proposed Waterfall architecture leverages the efficiency of progressive filtering in the cascade architecture while maintaining multiscale fields-of-view comparable to spatial pyramid configurations. Additionally, our method does not rely on a postprocessing stage with Conditional Random Fields, which further reduces complexity and required training time. We demonstrate that the Waterfall approach with a ResNet backbone is a robust and efficient architecture for semantic segmentation obtaining state-of-the-art results with significant reduction in the number of parameters for the Pascal VOC dataset and the Cityscapes dataset.
View Full-Text
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Artacho, B.; Savakis, A. Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation. Sensors 2019, 19, 5361. https://doi.org/10.3390/s19245361
AMA Style
Artacho B, Savakis A. Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation. Sensors. 2019; 19(24):5361. https://doi.org/10.3390/s19245361
Chicago/Turabian StyleArtacho, Bruno; Savakis, Andreas. 2019. "Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation" Sensors 19, no. 24: 5361. https://doi.org/10.3390/s19245361
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
Search more from Scilit
