Title: Image semantic segmentation based on improved DeepLab V3 model

Authors: Haifei Si; Zhen Shi; Xingliu Hu; Yizhi Wang; Chunping Yang

Addresses: College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China; College of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing, 211169, China ' College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China ' College of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing, 211169, China ' College of Intelligent Science and Control Engineering, Jinling Institute of Technology, Nanjing, 211169, China ' College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China

Abstract: To improve the image-segmentation speed based on the accuracy of a convolution neural network model, an improved DeepLab V3 network is proposed in this paper. The original feature extractor of DeepLab V3 is replaced with the lightweight network structure of MobileNet V2, and the original nonlinear activation function of a rectified linear unit is partially displaced by a new Swish activation function. Experimental results show that the improved DeepLab V3 network model can balance the segmentation accuracy and speed of the model better than the V3+ algorithm, which is the most accurate DeepLab network model till now. The running speed is improved significantly with a certain level of accuracy. In tests using different datasets, the running time decreased by 84% and 88.9%, and the model memory consumption decreased by approximately 96.6%. The improved DeepLab V3 network can adapt to deep-learning applications and satisfy their high-speed requirements.

Keywords: deep learning; DeepLab V3 model; lightweight; depth-wise separable convolution; semantic segmentation.

DOI: 10.1504/IJMIC.2020.116199

International Journal of Modelling, Identification and Control, 2020 Vol.36 No.2, pp.116 - 125

Received: 13 Jul 2020
Accepted: 12 Sep 2020
Published online: 13 Jul 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article