Dual-Pyramid Wide Residual Network for Semantic Segmentation on Cross-Style Datasets
-
Published:2023-11-24
Issue:12
Volume:14
Page:630
-
ISSN:2078-2489
-
Container-title:Information
-
language:en
-
Short-container-title:Information
Author:
Shen Guan-Ting1, Huang Yin-Fu2ORCID
Affiliation:
1. Innovation and Incubation Center, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi 600566, Taiwan 2. Department of Computer Science and Information Engineering, National Yunlin University of Science and Technology, Douliou 64002, Taiwan
Abstract
Image segmentation is the process of partitioning an image into multiple segments where the goal is to simplify the representation of the image and make the image more meaningful and easier to analyze. In particular, semantic segmentation is an approach of detecting the classes of objects, based on each pixel. In the past, most semantic segmentation models were for only one single style, such as urban street views, medical images, or even manga. In this paper, we propose a semantic segmentation model called the Dual-Pyramid Wide Residual Network (DPWRN) to solve the segmentation on cross-style datasets, which is suitable for diverse segmentation applications. The DPWRN integrated the Pyramid of Kernel paralleled with Dilation (PKD) and Multi-Feature Fusion (MFF) to improve the accuracy of segmentation. To evaluate the generalization of the DPWRN and its superiority over most state-of-the-art models, three datasets with completely different styles are tested in the experiments. As a result, our model achieves 75.95% of mIoU on CamVid, 83.60% of F1-score on DRIVE, and 86.87% of F1-score on eBDtheque. This verifies that the DPWRN can be generalized and shows its superiority in semantic segmentation on cross-style datasets.
Subject
Information Systems
Reference55 articles.
1. Simonyan, K., and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv. 2. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA. 3. Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA. 4. Yu, F., and Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. arXiv. 5. Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv.
|
|