Unsupervised Semantic Segmentation Inpainting Network Using a Generative Adversarial Network with Preprocessing
-
Published:2023-01-05
Issue:2
Volume:13
Page:781
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Ahn Woo-JinORCID, Kim Dong-WonORCID, Kang Tae-KooORCID, Pae Dong-SungORCID, Lim Myo-TaegORCID
Abstract
The generative adversarial neural network has shown a novel result in the image generation area. However, applying it to a semantic segmentation inpainting task exhibits instability due to the different data distribution. To solve this problem, we propose an unsupervised semantic segmentation inpainting method using an adversarial deep neural network with a newly introduced preprocessing method and loss function. For stabilizing the adversarial training for semantic segmentation inpainting, we match the probability distribution of the segmentation maps with the developed preprocessing method. In addition, a new cross-entropy total variation loss for the probability map is introduced to improve the segmentation inpainting work by smoothing the segmentation map. The experimental results demonstrate the proposed algorithm’s effectiveness on both synthetic and real datasets.
Funder
National Research Foundation of Korea
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference40 articles.
1. Ivanovs, M., Ozols, K., Dobrajs, A., and Kadikis, R. (2022). Improving semantic segmentation of urban scenes for self-driving cars with synthetic images. Sensors, 22. 2. Yao, J., Ramalingam, S., Taguchi, Y., Miki, Y., and Urtasun, R. (2015, January 5–9). Estimating drivable collision-free space from monocular video. Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA. 3. Jiménez, F., Clavijo, M., and Cerrato, A. (2022). Perception, positioning and decision-making algorithms adaptation for an autonomous valet parking system based on infrastructure reference points using one single LiDAR. Sensors, 22. 4. Lai, X., Tian, Z., Xu, X., Chen, Y., Liu, S., Zhao, H., Wang, L., and Jia, J. (2022, January 23–27). DecoupleNet: Decoupled network for domain adaptive semantic segmentation. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel. 5. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.
|
|