当前位置:
X-MOL 学术
›
arXiv.cs.CV
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Interactive Learning for Semantic Segmentation in Earth Observation
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-09-23 , DOI: arxiv-2009.11250 Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari, Bertrand Le Saux, Guy Le Besnerais
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-09-23 , DOI: arxiv-2009.11250 Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari, Bertrand Le Saux, Guy Le Besnerais
Dense pixel-wise classification maps output by deep neural networks are of
extreme importance for scene understanding. However, these maps are often
partially inaccurate due to a variety of possible factors. Therefore, we
propose to interactively refine them within a framework named DISCA (Deep Image
Segmentation with Continual Adaptation). It consists of continually adapting a
neural network to a target image using an interactive learning process with
sparse user annotations as ground-truth. We show through experiments on three
datasets using synthesized annotations the benefits of the approach, reaching
an IoU improvement up to 4.7% for ten sampled clicks. Finally, we exhibit that
our approach can be particularly rewarding when it is faced to additional
issues such as domain adaptation.
中文翻译:
地球观测中语义分割的交互式学习
深度神经网络输出的密集像素分类图对于场景理解极其重要。然而,由于各种可能的因素,这些地图往往部分不准确。因此,我们建议在名为 DISCA(具有持续适应的深度图像分割)的框架内交互式地改进它们。它包括使用交互式学习过程将神经网络不断适应目标图像,并将稀疏用户注释作为真实情况。我们通过使用合成注释的三个数据集的实验展示了该方法的好处,十次采样点击的 IoU 改进高达 4.7%。最后,我们展示了我们的方法在面临域适应等其他问题时特别有益。
更新日期:2020-09-24
中文翻译:
地球观测中语义分割的交互式学习
深度神经网络输出的密集像素分类图对于场景理解极其重要。然而,由于各种可能的因素,这些地图往往部分不准确。因此,我们建议在名为 DISCA(具有持续适应的深度图像分割)的框架内交互式地改进它们。它包括使用交互式学习过程将神经网络不断适应目标图像,并将稀疏用户注释作为真实情况。我们通过使用合成注释的三个数据集的实验展示了该方法的好处,十次采样点击的 IoU 改进高达 4.7%。最后,我们展示了我们的方法在面临域适应等其他问题时特别有益。