图 书 馆
利用广义归一化变换的图像密度建模Density Modeling of Images using a Generalized Normalization Transformation |
|
| 课程网址: | http://videolectures.net/iclr2016_balle_density_modeling/ |
| 主讲教师: | Johannes Ballé |
| 开课单位: | 纽约大学 |
| 开课时间: | 2016-06-15 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We introduce a parametric nonlinear transformation that is well-suited for Gaussianizing data from natural images. The data are linearly transformed, and each component is then normalized by a pooled activity measure, computed by exponentiating a weighted sum of rectified and exponentiated components and a constant. We optimize the parameters of the full transformation (linear transform, exponents, weights, constant) over a database of natural images, directly minimizing the negentropy of the responses. The optimized transformation substantially Gaussianizes the data, achieving a significantly smaller mutual information between transformed components than alternative methods including ICA and radial Gaussianization. The transformation is differentiable and can be efficiently inverted, and thus induces a density model on images. We show that samples of this model are visually similar to samples of natural image patches. We demonstrate the use of the model as a prior probability density that can be used to remove additive noise. Finally, we show that the transformation can be cascaded, with each layer optimized using the same Gaussianization objective, thus offering an unsupervised method of optimizing a deep network architecture. |
| 关 键 词: | 自然图像; 线性变换; 数据转换 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-04-03：chenxin01 |
| 最后编审: | 2023-05-22：chenxin01 |
| 阅读次数: | 19 |