LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation

06/14/2017
by   Abhishek Chaurasia, et al.
0

Pixel-wise semantic segmentation for visual scene understanding not only needs to be accurate, but also efficient in order to find any use in real-time application. Existing algorithms even though are accurate but they do not focus on utilizing the parameters of neural network efficiently. As a result they are huge in terms of parameters and number of operations; hence slow too. In this paper, we propose a novel deep neural network architecture which allows it to learn without any significant increase in number of parameters. Our network uses only 11.5 million parameters and 21.2 GFLOPs for processing an image of resolution 3x640x360. It gives state-of-the-art performance on CamVid and comparable results on Cityscapes dataset. We also compare our networks processing time on NVIDIA GPU and embedded system device with existing state-of-the-art architectures for different image resolutions.

READ FULL TEXT
research
06/07/2016

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

The ability to perform pixel-wise semantic segmentation in real-time is ...
research
05/19/2021

Dynamic region proposal networks for semantic segmentation in automated glaucoma screening

Screening for the diagnosis of glaucoma through a fundus image can be de...
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
04/04/2019

Template-Based Automatic Search of Compact Semantic Segmentation Architectures

Automatic search of neural architectures for various vision and natural ...
research
04/03/2019

MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks

Real-time image semantic segmentation is an essential capability to enha...
research
01/21/2021

Ikshana: A Theory of Human Scene Understanding Mechanism

In recent years, deep neural networks achieved state-of-the-art performa...
research
12/06/2019

Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

We propose a new efficient architecture for semantic segmentation, based...

Please sign up or login with your details

Forgot password? Click here to reset