Wide Residual Networks for Semantic Segmentation
Wide Residual Networks for Semantic Segmentation
复制标题
DOI：
--
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
Yoshiki Nakayama;Huimin LU-;Yujie Li;Hyoungseop Kim
中科院分区：
文献类型：
--
作者：
Yoshiki Nakayama;Huimin LU-;Yujie Li;Hyoungseop Kim
在目标识别任务中，卷积神经网络（CNN）取得了很高的性能。此外，这些CNN还应用于语义图像分割领域。然而，将分类模型应用于语义分割任务存在一个问题，即缺乏全局上下文和分辨率降低。在这项工作中，我们提出了全局上下文模块和高分辨率路径来解决上述问题。通过简单地将它们与现有的分类模型（宽残差网络）相结合，我们的方法就可以产生高精度的分割模型。我们提出的方法在 CamVid 测试集上产生了有竞争力的结果，平均交集 (IoU) 为 67.6%，全局准确度为 91.1%。
In the task of object recognition, convolutional neural networks (CNNs) have achieved high performance. In addition, these CNNs are also applied to the field of semantic image segmentation. However, applying the classification models to semantic segmentation tasks has a problem, lack of global context and reduction in resolution. In this work, we propose global context module and high resolution path in order to solve above problems. By simply combining them with an existing classification model (wide residual networks), our methods yield high-accuracy segmentation models. Our proposed approaches produce competitive results, the mean intersection over union (IoU) 67.6% and global accuracy 91.1%, on CamVid test set.