Neural Diffusion Distance for Image Segmentation
Neural Diffusion Distance for Image Segmentation
复制标题
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Jian Sun-;Zongben Xu
中科院分区：
文献类型：
--
作者：
Jian Sun-;Zongben Xu
扩散距离是一种考虑全局数据结构的度量图上节点间距离的谱方法。在这项工作中，我们提出了一个spec-diff-net计算扩散距离的基础上近似谱分解图。该网络是一个可微分的深度架构，由特征提取和扩散距离模块组成，用于通过端到端训练计算图像上的扩散距离。我们设计了低分辨率核匹配损失和高分辨率段匹配损失，以强制网络的输出与人类标记的图像段一致。为了计算高分辨率的扩散距离或分割掩码，我们设计了一种通过特征注意插值的上采样策略，该策略可以在训练spec-diff-net时学习。利用学习到的扩散距离，我们提出了一种优于以往分割方法的分层图像分割方法。此外，利用扩散距离设计了一个弱监督语义分割网络，并在PASCAL VOC 2012分割数据集上取得了令人满意的结果。
Diffusion distance is a spectral method for measuring distance among nodes on graph considering global data structure. In this work, we propose a spec-diff-net for computing diffusion distance on graph based on approximate spectral decomposition. The network is a differentiable deep architecture consisting of feature extraction and diffusion distance modules for computing diffusion distance on image by end-to-end training. We design low resolution kernel matching loss and high resolution segment matching loss to enforce the network's output to be consistent with human-labeled image segments. To compute high-resolution diffusion distance or segmentation mask, we design an up-sampling strategy by feature-attentional interpolation which can be learned when training spec-diff-net. With the learned diffusion distance, we propose a hierarchical image segmentation method outperforming previous segmentation methods. Moreover, a weakly supervised semantic segmentation network is designed using diffusion distance and achieved promising results on PASCAL VOC 2012 segmentation dataset.