Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

12/06/2019
by   Bruno Artacho, et al.
22

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.

READ FULL TEXT

page 3

page 4

page 5

page 7

page 9

page 10

page 13

page 18

research
01/22/2020

UniPose: Unified Human Pose Estimation in Single Images and Videos

We propose UniPose, a unified framework for human pose estimation, based...
research
05/27/2015

Improving Spatial Codification in Semantic Segmentation

This paper explores novel approaches for improving the spatial codificat...
research
04/03/2019

DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

This paper introduces an extremely efficient CNN architecture named DFAN...
research
07/06/2020

Exploration of Optimized Semantic Segmentation Architectures for edge-Deployment on Drones

In this paper, we present an analysis on the impact of network parameter...
research
06/14/2017

LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation

Pixel-wise semantic segmentation for visual scene understanding not only...
research
12/20/2021

BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations

We propose BAPose, a novel bottom-up approach that achieves state-of-the...
research
07/17/2023

On the Real-Time Semantic Segmentation of Aphid Clusters in the Wild

Aphid infestations can cause extensive damage to wheat and sorghum field...

Please sign up or login with your details

Forgot password? Click here to reset