Improved Lightweight Semantic Segmentation Algorithm Based on DeepLabv3<bold>+</bold> Network

Table 1. Experimental parameters
View table
Table 1. Experimental parameters
Parameter name Parameter selection
Enter picture size 769×769
Loss function Cross entropy
Optimizer SGD
Batch size 16
Iteration 18500

Table 2. Comparison of Deeplabv3+ model performance of different backbone networks
View table
Table 2. Comparison of Deeplabv3+ model performance of different backbone networks
Evaluation index Xception ResNet-50 MobileNetv3
mIoU /% 78.18 79.20 72.94
Validating time /ms 113 234 15
Parameter quantity /MB 78.53 38.72 2.18

Table 3. Comparison of different convolution methods
View table
Table 3. Comparison of different convolution methods
Convolution method in ASPP Training time /h mIoU /%
Standard convolution 3.39 68.50
Depthwise separable convolution in ASPP 2.56 66.78

Table 4. Performance results for different modules on Cityscape
View table
Table 4. Performance results for different modules on Cityscape
Depthwise separable convolution in ASPP SE GN mIoU /%
68.50
√ 66.78
√ 71.23
√ √ 70.17
√ √ √ 72.94

Table 5. Performance results for different modules on Foggy Cityscape
View table
Table 5. Performance results for different modules on Foggy Cityscape
Depthwise separable convolution in ASPP SE GN mIoU /%
54.06
√ 53.42
√ 57.71
√ √ 56.31
√ √ √ 58.76

Table 6. Comparison of performance of different algorithms

View table

Table 6. Comparison of performance of different algorithms

Algorithm	Backbone network	mIoU /%	Parameter quantity /MB
PSPNet^［14］	Paper source	78.42	84.75
SegNet^［8］	Paper source	57.95	29.46
DeepLabv3+	Xception	78.18	78.53
DeepLabv3+	ResNet-50	79.20	38.72
Proposed algorithm	MobileNetv3	72.94	2.18

Table 7. Comparison of lightweight image semantic segmentation algorithms
View table
Table 7. Comparison of lightweight image semantic segmentation algorithms
Algorithm mIoU /% Parameter quantity /MB
FSSNet^［23］ 62.32 0.20
Fast-SCNN^［24］ 69.25 2.33
ENet^［25］ 60.43 0.37
Proposed algorithm 72.94 2.18

Tools

Get Citation

Copy Citation Text

Yan Yao, Likun Hu, Jun Guo. Improved Lightweight Semantic Segmentation Algorithm Based on DeepLabv3+ Network[J]. Laser & Optoelectronics Progress, 2022, 59(4): 0410015

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites