Laser & Optoelectronics Progress, Volume. 56, Issue 15, 150003(2019)
Review of Deep Learning-Based Semantic Segmentation
Figures & Tables(18)
Fig. 6. Partial dataset images and corresponding semantic segmentation effect diagrams. (a) PASCAL VOC 2012; (b) PASCAL-CONTEXT; (c) MICROSOFT COCO; (d) CITYSCAPES
Fig. 10. Effects of using CRF tuning iterations in DeepLab. (a) GT; (b) CNNout; (c) CRFit1; (d) CRFit2; (e) CRFit10
Table 1. Information summary of common image classification networks
View tableTable 1. Information summary of common image classification networks
Item LeNet5 AlexNet VGGNet GoogLeNet ResNet Year 1994 2012 2014 2014 2015 Layer 7 8 19 22 152 Conv 2 5 16 21 151 Kernel size 5 11,5,3 3 7,1,3,5 7,1,3,5 Linear 3 3 3 1 1 Linear size 120,84,10 4096,4096,1000 4096,4096,1000 1000 1000 Activation function Sigmoid ReLU ReLU ReLU ReLU Classifier Multi-layer perception Softmax Softmax Softmax Softmax Data augment × √ √ √ √ Bath normalization × × × × √ Local response normalization × √ × √ × Graphics processing unit × √ √ √ √ Inception × × × √ × Dropout × √ √ √ √ TOP-5(error) N/A 16.4% 7.32% 6.67% 3.57%
Table 2. Information summary of common semantic segmentation datasets
View tableTable 2. Information summary of common semantic segmentation datasets
Dataset Classes Sample(training) Sample(validation) Sample(test) Purpose Year PASCAL VOC 2012[ 18 ]21 1464 1449 1452 Generic 2012 PASCAL VOC 2012+[ 19 ]21 10582 1449 1452 Generic 2014 PASCAL-CONTEXT[ 20 ]540 4998 5105 - Generic 2014 PASCAL-PERSON-PART[ 20 ]6 1716 - 1817 Person 2014 PASCAL-COW-PART[ 21 ]4 294 - 227 Cow 2015 SBD[ 22 ]21 8498 2857 - Generic 2011 MICROSOFT COCO[ 23 ]80+ 82783 40504 81434 Generic 2014 CITYSCAPES(fine)[ 24 ]19 2975 500 1525 Urban 2015 CITYSCAPES(coarse)[ 24 ]19 22973 500 - Urban 2015 CAMVID[ 25 -26 ]32 361 100 233 Driving 2009 KITTI-Ros[ 27 ]11 170 - 46 Driving 2015 KITTI-Zhang[ 28 ]10 140 - 112 Driving 2015
Table 3. Information summary of common deep learning semantic segmentation methods
View tableTable 3. Information summary of common deep learning semantic segmentation methods
Model name Year Architecture Accuracy Efficiency Training Contribution FCN[ 32 ]2015 VGG-16(FCN) C C C Forerunner SegNet[ 33 ]2017 VGG-16 + Decoder A B C Encoder-decoder DeepLab[ 34 -37 ]2017 VGG-16 + ResNet-101 A C C Standalone CRF, Atrous convolutions CRFasRNN[ 38 ]2015 FCN-8s C B A CRF reformulated as RNN ParseNet[ 39 ]2015 VGG-16 A C C Global context feature fusion SharpMask [ 40 ]2016 DeepMask A C C Top-down refinement module PSPNet[ 41 ]2016 ResNet-101 A B C Pyramid pooling module Multi-scale- CNN-Raj[ 42 ]2015 VGG-16(FCN) A C C Multi-scale architecture Multi-scale- CNN-Eigen[ 43 ]2015 Custom A C C Multi-scale sequential refinement Multi-scale- CNN-Roy[ 44 ]2016 Multi-scale-CNN-Eigen A C C Multi-scale coarse- to-fine refinement Multi-scale- CNN-Bian[ 45 ]2016 FCN B C B Independently trained Multi-scale FCNs ReSeg[ 46 ]2016 VGG-16 + ReNet B C C Extension of ReNet to semantic segmentation LSTM-CF[ 47 ]2016 Fast R-CNN +DeepMask A C C Fusion of contextualinformation from multiple sources RCNN[ 48 ]2014 MDRNN A B C Different input sizes, image context 2D-LSTM[ 49 ]2015 MDRNN B B C Image context modelling DAG-RNN [ 50 ]2015 Elman network A C C Graph image structure for context modelling MINC-CNN[ 51 ]2015 GoogLeNet(FCN) C C C Patchwise CNN, Standalone CRF DeepMask[ 52 ]2015 VGG-A A C C Proposals generation for segmentation
Tools
Get Citation
Copy Citation Text
Xiangfu Zhang, Jian Liu, Zhangsong Shi, Zhonghong Wu, Zhi Wang. Review of Deep Learning-Based Semantic Segmentation[J]. Laser & Optoelectronics Progress, 2019, 56(15): 150003
Paper Information
Category: Reviews
Received: Jan. 25, 2019
Accepted: Mar. 5, 2019
Published Online: Aug. 5, 2019
The Author Email: Liu Jian (liujian_nue@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20