图 书 馆
高斯边势全连通crf的有效推理Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials |
|
| 课程网址: | http://videolectures.net/nips2011_kraehenbuehl_potentials/ |
| 主讲教师: | Philipp Krähenbühl |
| 开课单位: | 加州大学 |
| 开课时间: | 2012-01-25 |
| 课程语种: | 英语 |
| 中文简介: |  用于多类图像分割和标记的大多数最新技术使用在像素或图像区域上定义的条件随机字段。尽管区域级模型通常具有密集的成对连通性，但像素级模型却要大得多，并且只允许稀疏图结构。在本文中，我们考虑在图像的完整像素集上定义的完全连接的CRF模型。生成的图具有数十亿条边，这使得传统的推理算法不切实际。我们的主要贡献是针对全连接CRF模型的高效近似推理算法，其中成对边缘电势由高斯核的线性组合定义。我们的算法可以在几分之一秒内最大程度地减少成千上万个变量的完全连接模型。 MSRC 21和PASCAL VOC 2010数据集的定量和定性结果表明，像素级的完全成对连通性可以产生更加准确的分割和像素级标签分配。 |
| 课程简介: | Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level 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 linear combinations of Gaussian kernels. Our algorithm can approximately minimize fully connected models on tens of thousands of variables in a fraction of a second. Quantitative and qualitative results on the MSRC-21 and PASCAL VOC 2010 datasets demonstrate that full pairwise connectivity at the pixel level produces significantly more accurate segmentations and pixel-level label assignments. |
| 关 键 词: | 推理算法; 线性组合 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-11-16：zyk |
| 最后编审: | 2021-06-25：zyk |
| 阅读次数: | 80 |