首页> 外文期刊>IEEE Transactions on Pattern Analysis and Machine Intelligence >Learning from Weak and Noisy Labels for Semantic Segmentation
【24h】

Learning from Weak and Noisy Labels for Semantic Segmentation

机译:从弱和嘈杂的标签中学习语义分割

获取原文
获取原文并翻译 | 示例

摘要

A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the tedious pixel-level annotation process, it can exploit the unlimited supply of user-tagged images from media-sharing sites such as Flickr for large scale applications. However, these ‘free’ tags/labels are often noisy and few existing works address the problem of learning with both weak and noisy labels. In this work, we cast the WSSS problem into a label noise reduction problem. Specifically, after segmenting each image into a set of superpixels, the weak and potentially noisy image-level labels are propagated to the superpixel level resulting in highly noisy labels; the key to semantic segmentation is thus to identify and correct the superpixel noisy labels. To this end, a novel L1 -optimisation based sparse learning model is formulated to directly and explicitly detect noisy labels. To solve the L1 -optimisation problem, we further develop an efficient learning algorithm by introducing an intermediate labelling variable. Extensive experiments on three benchmark datasets show that our method yields state-of-the-art results given noise-free labels, whilst significantly outperforming the existing methods when the weak labels are also noisy.
机译:弱监督语义分割(WSSS)方法旨在从弱(图像级别)标签到强(像素级别)标签学习分割模型。通过避免繁琐的像素级注释过程,它可以将来自媒体共享站点(例如Flickr)的用户标记图像的无限供应用于大规模应用。但是,这些“免费”标签/标签通常很吵,现有的作品很少解决弱标签和吵标签的学习问题。在这项工作中,我们将WSSS问题转换为标签降噪问题。具体来说,在将每个图像分割成一组超像素之后,弱且可能有噪声的图像级标签将传播到超像素级,从而导致高噪声标签。因此,语义分割的关键是识别和纠正超像素噪声标签。为此,制定了一种新颖的基于L1优化的稀疏学习模型来直接和显式地检测噪声标签。为了解决L1优化问题,我们通过引入中间标记变量进一步开发了一种有效的学习算法。在三个基准数据集上进行的大量实验表明,在无噪声标签的情况下,我们的方法可获得最先进的结果,而当弱标签也很嘈杂时,该方法的性能明显优于现有方法。

著录项

  • 来源
  • 作者单位

    Beijing Key Laboratory of Big Data Management and Analysis Methods, School of Information, Renmin University of China, Beijing, China;

    School of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London, United Kingdom;

    School of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London, United Kingdom;

    Beijing Key Laboratory of Big Data Management and Analysis Methods, School of Information, Renmin University of China, Beijing, China;

    School of Electronics Engineering and Computer Science, Peking University, Beijing, China;

    Computational Bioscience Research Center (CBRC), CEMSE Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Noise measurement; Image segmentation; Semantics; Noise reduction; Training; Computational modeling; Labeling;

    机译:噪声测量;图像分割;语义;降噪;训练;计算模型;标签;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号