【论文笔记】Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

最新推荐文章于 2021-03-20 21:13:38 发布

xiaxzhou

最新推荐文章于 2021-03-20 21:13:38 发布

阅读量5.9k

点赞数 1

分类专栏：论文

本文链接：https://blog.csdn.net/xiaxzhou/article/details/74065257

版权

该文提出了一种针对全连接条件随机场（CRF）模型的高效近似推理算法，尤其适用于具有高斯核的像素间势函数。在大规模图像分割和标记任务中，通过在特征空间中应用高斯滤波，实现了从二次到线性的计算复杂度降低，显著提升了像素级的分割和标签准确性。

摘要由CSDN通过智能技术生成

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

摘要：

most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. while regionlevel models often feature dense pairwise connectivity, pixel-level models are considerably larger and have only permitted sparse graph structures. in this paper, we consider fully connected crf models defined on the complete set of pixels in an image. the resulting graphs have billions of edges, making traditional inference algorithms impractical. our main contribution is a highly efficient approximate inference algorithm for fully connected crf models in which the pairwise edge potentials are defined by a linear combination of gaussian kernels. our experiments demonstrate that dense connectivity at the pixel level substantia s