Weakly supervised conditional random fields model for semantic segmentation with image patches

Xu, Xinying and Xue, Yujing and Han, Xiaoxia and Zhang, Zhe and Xie, Jue and Ren, Jinchang (2020) Weakly supervised conditional random fields model for semantic segmentation with image patches. Applied Sciences, 10 (5). 1679. ISSN 2076-3417 (https://doi.org/10.3390/app10051679)

[thumbnail of Xu-etal-AS-2020-Weakly-supervised-conditional-random-fields-model-for-semantic-segmentation]
Text. Filename: Xu_etal_AS_2020_Weakly_supervised_conditional_random_fields_model_for_semantic_segmentation.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo

Download (4MB)| Preview


Image semantic segmentation (ISS) is used to segment an image into regions with differently labeled semantic category. Most of the existing ISS methods are based on fully supervised learning, which requires pixel-level labeling for training the model. As a result, it is often very time-consuming and labor-intensive, yet still subject to manual errors and subjective inconsistency. To tackle such difficulties, a weakly supervised ISS approach is proposed, in which the challenging problem of label inference from image-level to pixel-level will be particularly addressed, using image patches and conditional random fields (CRF). An improved simple linear iterative cluster (SLIC) algorithm is employed to extract superpixels. for image segmentation. Specifically, it generates various numbers of superpixels according to different images, which can be used to guide the process of image patch extraction based on the image-level labeled information. Based on the extracted image patches, the CRF model is constructed for inferring semantic class labels, which uses the potential energy function to map from the image-level to pixel-level image labels. Finally, patch based CRF (PBCRF) model is used to accomplish the weakly supervised ISS. Experiments conducted on two publicly available benchmark datasets, MSRC and PASCAL VOC 2012, have demonstrated that our proposed algorithm can yield very promising results compared to quite a few state-of-the-art ISS methods, including some deep learning-based models.


Xu, Xinying, Xue, Yujing, Han, Xiaoxia, Zhang, Zhe, Xie, Jue and Ren, Jinchang ORCID logoORCID: https://orcid.org/0000-0001-6116-3194;