This paper proposes an affinity fusion graph framework to effectively connect different graphs with highly discriminating power and nonlinearity for natural image segmentation. The proposed framework combines adjacency-graphs and kernel spectral clustering based graphs (KSC-graphs) according to a new definition named affinity nodes of multi-scale superpixels. These affinity nodes are selected based on a better affiliation of superpixels, namely subspace-preserving representation which is generated by sparse subspace clustering based on subspace pursuit. Then a KSC-graph is built via a novel kernel spectral clustering to explore the nonlinear relationships among these affinity nodes. Moreover, an adjacency-graph at each scale is constructed, which is further used to update the proposed KSC-graph at affinity nodes. The fusion graph is built across different scales, and it is partitioned to obtain final segmentation result. Experimental results on the Berkeley segmentation dataset and Microsoft Research Cambridge dataset show the superiority of our framework in comparison with the state-of-the-art methods. The code is available at https://github.com/Yangzhangcst/AF-graph.
翻译:本文提出一个近似聚合图解框架, 以有效地将不同图表与高度区别的能量和自然图像分化的非线性相连接。 拟议的框架根据名为“ 多比例超像的亲和结点” 的新定义, 将相邻- 光谱群集图( KSC- graphs) 和内核光谱集图( KSC- graphs) 结合起来。 这些亲和结点是根据超像素的更好属性选择的, 即基于子空间追求的稀疏子空间聚集产生的亚空间保护代表。 然后, 通过新颖的内核光谱聚集建立 KSC graph, 以探索这些相亲性节点之间的非线性关系。 此外, 在每个尺度上都构建了相邻性图谱图( KSC- graphs), 用于在亲和交点上更新拟议的KSC- graphs。 聚点是在不同尺度上建的, 并且为了获得最终的分解结果, 。 Berkeley 分区数据集 和 Microsoft 研究剑桥数据集的实验结果显示我们框架的优越性与州- 和Yqubs/ 的方法。 。 。 在 ambs/ http/ hang/ a. 上可以提供的代码。