期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 233, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2023.120973
关键词
Semi-supervised semantic segmentation; Multi-reliability feature augmentation; Multi-level feature augmentation; Data perturbation
Semi-supervised semantic segmentation aims to classify pixels using both labeled and unlabeled images. The utilization of unlabeled images is crucial in semi-supervised learning. Existing methods tend to focus on reliable pixels while ignoring unreliable pixels, resulting in information loss. Uneven distribution of pixels per category can also lead to misclassification.
Semi-supervised semantic segmentation aims to classify the pixels with both labeled and unlabeled images. How to utilize unlabeled images is a key part of semi-supervised learning. The existing methods tend to exploit the reliable pixels which can be classified to a specific category with high reliability, ignoring the unreliable pixels which cannot be identified into a special category with low reliability, resulting in information loss. Moreover, uneven number of pixels per category often leads to misclassification of small-scale category pixels. In this paper, we propose a multi-reliability and multi-level feature augmentation framework. Multi-reliability feature augmentation dedicates to extract unreliable/reliable pixel features to take full advantage of pixel information. Multi-level feature augmentation dedicates to extract category/image level semantic features to avoid the sparse semantic information provided by category with a small number of pixels, which can lead to misclassification. Furthermore, a variety of data perturbations are employed to enhance the robustness of our model. Experimental results on the PASCAL VOC 2012, Cityscapes datasets verify the effectiveness of our method. Our code is available at https://github.com/JianJianYin/MMFA.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据