Semantic Segmentation Using Trade-Off and Internal Ensemble

Jeon, Wang-Su, Cielniak, Grzegorz and Sang-Yong, Rhee (2018) Semantic Segmentation Using Trade-Off and Internal Ensemble. International Journal of Fuzzy Logic and Intelligent Systems, 18 (3). pp. 196-203. ISSN 1598-2645

Full content URL:

Semantic Segmentation Using Trade-Off and Internal Ensemble
Publisher's final pdf
[img] PDF
ijfis-18-196.pdf - Whole Document
Available under License Creative Commons Attribution-NonCommercial 4.0 International.

Item Type:Article
Item Status:Live Archive


The computer vision consists of image classification, image segmentation, object detection, and tracking, etc. Among them, image segmentation is the most basic technique of the computer vision, which divides an image into foreground and background. This paper proposes an ensemble model using a concept of physical perception for image segmentation. Practically two connected models, the DeepLab and a modified VGG model, get feedback each other in the training process. On inference processing, we combine the results of two parallel models and execute an atrous spatial pyramid pooling (ASPP) and post-processing by using conditional random field (CRF). The proposed model shows better performance than the DeepLab in local area and about 1% improvement on average on comparison of pixel-by-pixel.

Keywords:deep networks, semantic segmentation, computer vision
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:34496
Deposited On:12 Feb 2019 16:10

Repository Staff Only: item control page