Semantic Binary Segmentation Using Convolutional Networks without Decoders (2018-05-01T00:00:00.000000Z)

TL;DR

This paper proposes an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation, which eliminates the decoder portion of traditional encoder-decoder segmentation models and reduces the amount of computation almost by half.

Abstract

In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation. Our D2S model is comprised of a standard CNN encoder followed by a depth-to-space reordering of the final convolutional feature maps. Our approach eliminates the decoder portion of traditional encoder-decoder segmentation models and reduces the amount of computation almost by half. As a participant of the DeepGlobe Road Extraction competition, we evaluate our models on the corresponding road segmentation dataset. Our highly efficient D2S models exhibit comparable performance to standard segmentation models with much lower computational cost.

Authors

I. Stavness

7 papers

Shubhra Aich

3 papers

William van der Kamp

1 papers

Semantic Binary Segmentation Using Convolutional Networks without Decoders

TL;DR

Abstract

Authors

References30 items

DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images

DeepRoadMapper: Extracting Road Topology from Aerial Images

Creating Roadmaps in Aerial Images with Generative Adversarial Networks and Smoothing-Based Optimization

DeepWheat: Estimating Phenotypic Traits From Images of Crops Using Deep Learning

Leaf Counting with Deep Convolutional and Deconvolutional Networks

Rethinking Atrous Convolution for Semantic Image Segmentation

Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network

COCO-Stuff: Thing and Stuff Classes in Context

Pyramid Scene Parsing Network

RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Deep Residual Learning for Image Recognition

Multi-Scale Context Aggregation by Dilated Convolutions

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

Learning Deconvolution Network for Semantic Segmentation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

Adam: A Method for Stochastic Optimization

Object Detectors Emerge in Deep Scene CNNs

Efficient object localization using Convolutional Networks

Fully convolutional networks for semantic segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet Large Scale Visual Recognition Challenge

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

ImageNet classification with deep convolutional neural networks

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

using Deep Learning

The Devil is in the Decoders

Field of Study

Journal Information

Name

Page