Document Type

Journal Article

Publication Title

IEEE Access

Volume

12

First Page

117908

Last Page

117920

Publisher

IEEE

School

School of Engineering

Funders

King Khalid University (RGP.2/373/45)

Comments

Ibrahim, I. A., Namoun, A., Ullah, S., Alasmary, H., Waqas, M., & Ahmad, I. (2024). Infrared ship segmentation based on weakly-supervised and semi-supervised learning. IEEE Access, 12, 117908-117920. https://doi.org/10.1109/ACCESS.2024.3448301

Abstract

Existing fully-supervised semantic segmentation methods have achieved good performance. However, they all rely on high-quality pixel-level labels. To minimize the annotation costs, weakly-supervised methods or semi-supervised methods are proposed. When such methods are applied to the infrared ship image segmentation, inaccurate object localization occurs, leading to poor segmentation results. In this paper, we propose an infrared ship segmentation (ISS) method based on weakly-supervised and semi-supervised learning, aiming to improve the performance of ISS by combining the advantages of two learning methods. It uses only image-level labels and a minimal number of pixel-level labels to segment different classes of infrared ships. Our proposed method includes three steps. First, we designed a dual-branch localization network based on ResNet50 to generate ship localization maps. Second, we trained a saliency network with minimal pixel-level labels and many localization maps to obtain ship saliency maps. Then, we optimized the saliency maps with conditional random fields and combined them with image-level labels to generate pixel-level pseudo-labels. Finally, we trained the segmentation network with these pixel-level pseudo-labels to obtain the final segmentation results. Experimental results on the infrared ship dataset collected on real sites indicate that the proposed method achieves 71.18% mean intersection over union, which is at most 56.72% and 8.75% higher than the state-of-the-art weakly-supervised and semi-supervised methods, respectively.

DOI

10.1109/ACCESS.2024.3448301

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

 
COinS