分割
帕斯卡(单位)
计算机科学
人工智能
模式识别(心理学)
鉴别器
像素
图像分割
尺度空间分割
机器学习
电信
探测器
程序设计语言
作者
Huaian Chen,Yi Jin,Guoqiang Jin,Changan Zhu,Enhong Chen
出处
期刊:IEEE transactions on neural networks and learning systems
[Institute of Electrical and Electronics Engineers]
日期:2022-09-01
卷期号:33 (9): 4991-5003
被引量:12
标识
DOI:10.1109/tnnls.2021.3066850
摘要
Most of the recent image segmentation methods have tried to achieve the utmost segmentation results using large-scale pixel-level annotated data sets. However, obtaining these pixel-level annotated training data is usually tedious and expensive. In this work, we address the task of semisupervised semantic segmentation, which reduces the need for large numbers of pixel-level annotated images. We propose a method for semisupervised semantic segmentation by improving the confidence of the predicted class probability map via two parts. First, we build an adversarial framework that regards the segmentation network as the generator and uses a fully convolutional network as the discriminator. The adversarial learning makes the prediction class probability closer to 1. Second, the information entropy of the predicted class probability map is computed to represent the unpredictability of the segmentation prediction. Then, we infer the label-error map of the segmentation prediction and minimize the uncertainty on misclassified regions for unlabeled images. In contrast to existing semisupervised and weakly supervised semantic segmentation methods, the proposed method results in more confident predictions by focusing on the misclassified regions, especially the boundary regions. Our experimental results on the PASCAL VOC 2012 and PASCAL-CONTEXT data sets show that the proposed method achieves competitive segmentation performance.
科研通智能强力驱动
Strongly Powered by AbleSci AI