Cong Xu, Li Wang. Image Semantic Segmentation Method Based on Improved DeepLabv3+ Network[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610008
- Laser & Optoelectronics Progress
- Vol. 58, Issue 16, 1610008 (2021)
Fig. 1. Structure of the DeepLabv3+ network
Fig. 2. Structure of the improved DeepLabv3+ network
Fig. 3. Structure of the ASPP module
Fig. 4. Flow chart of the depth separable convolution
Fig. 5. Structure of the FPN
Fig. 6. Segmentation results of different methods. (a) Input image; (b) labeled image; (c) DeepLabv3+ network; (d) Ours 1
|
Table 1. Hardware and software configurations of the machine
|
Table 2. Test results under different combinations of dilation rate in ASPP module unit: %
|
Table 3. Training time and mIoU of different networks
|
Table 4. Performances of different networks
|
Table 5. mIoU of different networks on the PASCAL VOC2012 verification set
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20