Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation
Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation
复制标题
从噪声标签中进行大规模稀疏学习以进行语义分割
DOI：
10.1109/tcyb.2016.2631528
复制
发表时间：
2018-01-01
影响因子：
11.8
通讯作者：
Wen, Ji-Rong
中科院分区：
文献类型：
--
作者：
Li, Aoxue;Lu, Zhiwu;Wen, Ji-Rong
在本文中，我们提出了一个大规模的稀疏学习（LSSL）的方法来解决具有挑战性的任务，语义分割的图像与嘈杂的标签。与传统的利用像素级标签进行语义分割的强监督方法不同，我们使用弱得多的监督（即，图像的噪声标签），然后从超像素标签的降噪的角度将语义分割的任务公式化为弱监督学习（WSL）问题。通过学习数据流形，我们将WSL问题转化为LSSL问题。基于非线性近似和降维技术，提出了一种线性时间复杂度的算法来有效地求解LSSL问题。我们进一步扩展的LSSL方法的视觉特征细化语义分割。实验表明，所提出的LSSL方法可以实现有希望的结果在图像的噪声标签的语义分割。
In this paper, we present a large-scale sparse learning (LSSL) approach to solve the challenging task of semantic segmentation of images with noisy tags. Different from the traditional strongly supervised methods that exploit pixel-level labels for semantic segmentation, we make use of much weaker supervision (i.e., noisy tags of images) and then formulate the task of semantic segmentation as a weakly supervised learning (WSL) problem from the view point of noise reduction of superpixel labels. By learning the data manifolds, we transform the WSL problem into an LSSL problem. Based on nonlinear approximation and dimension reduction techniques, a linear-time-complexity algorithm is developed to solve the LSSL problem efficiently. We further extend the LSSL approach to visual feature refinement for semantic segmentation. The experiments demonstrate that the proposed LSSL approach can achieve promising results in semantic segmentation of images with noisy tags.