DeepAI AI Chat
Log In Sign Up

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

by   Vijay Badrinarayanan, et al.
University of Cambridge

We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder network followed by a pixel-wise classification layer. The architecture of the encoder network is topologically identical to the 13 convolutional layers in the VGG16 network. The role of the decoder network is to map the low resolution encoder feature maps to full input resolution feature maps for pixel-wise classification. The novelty of SegNet lies is in the manner in which the decoder upsamples its lower resolution input feature map(s). Specifically, the decoder uses pooling indices computed in the max-pooling step of the corresponding encoder to perform non-linear upsampling. This eliminates the need for learning to upsample. The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps. We compare our proposed architecture with the widely adopted FCN and also with the well known DeepLab-LargeFOV, DeconvNet architectures. This comparison reveals the memory versus accuracy trade-off involved in achieving good segmentation performance. SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference. It is also significantly smaller in the number of trainable parameters than other competing architectures. We also performed a controlled benchmark of SegNet and other architectures on both road scenes and SUN RGB-D indoor scene segmentation tasks. We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures. We also provide a Caffe implementation of SegNet and a web demo at


page 2

page 4

page 9

page 12

page 14


InfiNet: Fully Convolutional Networks for Infant Brain MRI Segmentation

We present a novel, parameter-efficient and practical fully convolutiona...

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling

We propose a novel deep architecture, SegNet, for semantic pixel wise im...

Dynamic Approach for Lane Detection using Google Street View and CNN

Lane detection algorithms have been the key enablers for a fully-assisti...

A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing

In this paper, we develop a binary convolutional encoder-decoder network...

OrthoSeg: A Deep Multimodal Convolutional Neural Network for Semantic Segmentation of Orthoimagery

This paper addresses the task of semantic segmentation of orthoimagery u...

CarNet: A Lightweight and Efficient Encoder-Decoder Architecture for High-quality Road Crack Detection

Pixel-wise crack detection is a challenging task because of poor continu...

Graph U-Nets

We consider the problem of representation learning for graph data. Convo...

Code Repositories


Implementation of SegNet: A Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-Wise Labelling

view repo


Files for a tutorial to train SegNet for road scenes using the CamVid dataset

view repo


This repository was a fork of BVLC/caffe and includes the upsample, bn, dense_image_data and softmax_with_loss (with class weighting) layers of caffe-segnet ( to run SegNet with cuDNN version 5.

view repo


Semantic image segmentation in Tensorflow

view repo


SegNet implementation & experiments in Chainer

view repo