计算机科学
帕斯卡(单位)
人工智能
分割
模式识别(心理学)
一致性(知识库)
像素
图像分割
计算机视觉
程序设计语言
作者
Linshan Wu,Leyuan Fang,Xingxin He,He Min,Jiayi Ma,Zhun Zhong
标识
DOI:10.1109/tpami.2022.3233584
摘要
Semi-supervised semantic segmentation aims to learn a semantic segmentation model via limited labeled images and adequate unlabeled images. The key to this task is generating reliable pseudo labels for unlabeled images. Existing methods mainly focus on producing reliable pseudo labels based on the confidence scores of unlabeled images while largely ignoring the use of labeled images with accurate annotations. In this paper, we propose a Cross-Image Semantic Consistency guided Rectifying (CISC-R) approach for semi-supervised semantic segmentation, which explicitly leverages the labeled images to rectify the generated pseudo labels. Our CISC-R is inspired by the fact that images belonging to the same class have a high pixel-level correspondence. Specifically, given an unlabeled image and its initial pseudo labels, we first query a guiding labeled image that shares the same semantic information with the unlabeled image. Then, we estimate the pixel-level similarity between the unlabeled image and the queried labeled image to form a CISC map, which guides us to achieve a reliable pixel-level rectification for the pseudo labels. Extensive experiments on the PASCAL VOC 2012, Cityscapes, and COCO datasets demonstrate that the proposed CISC-R can significantly improve the quality of the pseudo labels and outperform the state-of-the-art methods. Code is available at https://github.com/Luffy03/CISC-R.
科研通智能强力驱动
Strongly Powered by AbleSci AI