二阶池的语义分割Semantic Segmentation with Second-Order Pooling |
|
课程网址: | http://videolectures.net/eccv2012_carreira_semantic/ |
主讲教师: | Tinne Tuytelaars, João Carreira, Serge J. Belongie |
开课单位: | 科英布拉大学 |
开课时间: | 2012-11-12 |
课程语种: | 英语 |
中文简介: | 特征提取,编码和汇集是许多当代对象识别范例的重要组成部分。在本文中,我们探索了新的池化技术,它编码区域内局部描述符的二阶统计量。为了实现这种效果,我们引入了乘法平均值和最大值的二阶类似物,它们与适当的非线性一起导致自由形式区域识别的现有技术性能,而没有任何类型的特征编码。我们发现,使用额外的图像信息丰富本地描述符可以获得较大的性能,尤其是与所提出的池化方法相结合,而不是编码。我们表明,在自由形态区域上的二阶汇集产生的结果优于Pascal VOC 2011语义分段挑战中的获胜系统,其模型的速度要快20,000倍。 |
课程简介: | Feature extraction, coding and pooling, are important components on many contemporary object recognition paradigms. In this paper we explore novel pooling techniques that encode the second-order statistics of local descriptors inside a region. To achieve this effect, we introduce multiplicative second-order analogues of average and maxpooling that together with appropriate non-linearities lead to state-ofthe- art performance on free-form region recognition, without any type of feature coding. Instead of coding, we found that enriching local descriptors with additional image information leads to large performance gains, especially in conjunction with the proposed pooling methodology. We show that second-order pooling over freeform regions produces results superior to those of the winning systems in the Pascal VOC 2011 semantic segmentation challenge, with models that are 20,000 times faster. |
关 键 词: | 特征提取; 编码; 汇集 |
课程来源: | 视频讲座网 |
最后编审: | 2019-03-20:lxf |
阅读次数: | 256 |