Fast-SCNN: Fast Semantic Segmentation Network

02/12/2019
by   Rudra P K Poudel, et al.
12

The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional neural network (Fast-SCNN), an above real-time semantic segmentation model on high resolution image data (1024x2048px) suited to efficient computation on embedded devices with low memory. Building on existing two-branch methods for fast segmentation, we introduce our `learning to downsample' module which computes low-level features for multiple resolution branches simultaneously. Our network combines spatial detail at high resolution with deep features extracted at lower resolution, yielding an accuracy of 68.0 mean intersection over union at 123.5 frames per second on Cityscapes. We also show that large scale pre-training is unnecessary. We thoroughly validate our metric in experiments with ImageNet pre-training and the coarse labeled data of Cityscapes. Finally, we show even faster computation with competitive results on subsampled inputs, without any network modifications.

READ FULL TEXT

page 2

page 7

page 8

research
03/19/2018

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

We introduce a fast and efficient convolutional neural network, ESPNet, ...
research
05/11/2018

ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time

Modern deep learning architectures produce highly accurate results on ma...
research
12/01/2017

Real-time Semantic Image Segmentation via Spatial Sparsity

We propose an approach to semantic (image) segmentation that reduces the...
research
07/19/2018

Guided Upsampling Network for Real-Time Semantic Segmentation

Semantic segmentation architectures are mainly built upon an encoder-dec...
research
12/16/2022

Atrous Space Bender U-Net (ASBU-Net/LogiNet)

With recent advances in CNNs, exceptional improvements have been made in...
research
02/19/2020

Meta Segmentation Network for Ultra-Resolution Medical Images

Despite recent progress on semantic segmentation, there still exist huge...
research
04/06/2020

Fair Latency-Aware Metric for real-time video segmentation networks

As supervised semantic segmentation is reaching satisfying results, many...

Please sign up or login with your details

Forgot password? Click here to reset