Laser & Optoelectronics Progress, Volume. 59, Issue 16, 1610009(2022)
Optimization of Image Semantic Segmentation Algorithms Based on Deeplab v3+
Fig. 1. Deeplab v3+ model
Fig. 2. Standard convolution
Fig. 3. Depthwise separable convolution
Fig. 4. Overview of N-Deeplab v3+ model architecture
Fig. 5. Depthwise separable atrous convolution
Fig. 6. Influence of hetero-receptive field splicing on sampling points. (a) Sampling point distribution of convolution with rate of 12; (b) sampling point distribution of cascaded convolution with rates of (6 12)
Fig. 7. Feature alignment module based on attention mechanism
Fig. 8. Comparison of segmentation results on Cityscapes validation set. (a) Input images; (b) label images; (c) segmentation results of Deeplab v3+; (d) segmentation results of N-Deeplab v3+
Fig. 9. Comparison of segmentation results on PASCAL VOC 2012 verification set. (a) Input images; (b) label images; (c) segmentation results of Deeplab v3+; (d) segmentation results of N-Deeplab v3+
|
|
|
|
|
|
Get Citation
Copy Citation Text
Junxi Meng, Li Zhang, Yang Cao, Letian Zhang, Qian Song. Optimization of Image Semantic Segmentation Algorithms Based on Deeplab v3+[J]. Laser & Optoelectronics Progress, 2022, 59(16): 1610009
Category: Image Processing
Received: Jun. 7, 2021
Accepted: Jul. 9, 2021
Published Online: Jul. 22, 2022
The Author Email: Zhang Li (dx_zhangli@126.com)