Label Refinement Network for Coarse-to-Fine Semantic Segmentation
Label Refinement Network for Coarse-to-Fine Semantic Segmentation
复制标题
DOI：
--
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Md. Amirul Islam;Shujon Naha;Mrigank Rochan;Neil D. B. Bruce;Yang Wang
中科院分区：
文献类型：
--
作者：
Md. Amirul Islam;Shujon Naha;Mrigank Rochan;Neil D. B. Bruce;Yang Wang
我们考虑使用深度卷积神经网络进行语义图像分割的问题。我们提出了一种称为标签细化网络的新型网络架构，该网络以几种分辨率以粗到细的方式预测分割标签。粗分辨率的分割标签与卷积特征一起使用以获得更精细分辨率的分割标签。我们在网络的几个阶段定义损失函数，以提供不同阶段的监督。我们在几个标准数据集上的实验结果表明，该模型提供了一种有效的方法来产生像素级的密集图像标记。
We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions. The segmentation labels at a coarse resolution are used together with convolutional features to obtain finer resolution segmentation labels. We define loss functions at several stages in the network to provide supervisions at different stages. Our experimental results on several standard datasets demonstrate that the proposed model provides an effective way of producing pixel-wise dense image labeling.