Reducing the number of masks to accelerate the neural network visualization of RISE
Reducing the number of masks to accelerate the neural network visualization of RISE
复制标题
减少掩模数量以加速RISE的神经网络可视化
DOI：
10.1117/12.2666680
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Kousuke Imamura
中科院分区：
文献类型：
--
作者：
Tomoki Nakada;Kousuke Imamura
RISE是图像识别中用于可视化神经网络决策基础的方法之一。Rise创建热图，通过观察网络的响应，同时使用随机遮罩部分遮挡输入图像，从而显示图像各个部分的重要性。然而，这种方法需要大量的掩模图像才能获得平稳性，从而导致巨大的计算时间。在这项研究中，除了改进的随机掩码之外，我们还使用了只通过一个有限区域的非随机补丁掩码来减少所需的掩码数量，从而加快了上升过程。
RISE is one of the methods used for visualizing the basis of neural network decisions in image recognition. RISE creates a heat map showing the importance of various parts of an image by observing the response of the network while partially obscuring the input image with a random mask. However, this method requires many mask images to obtain stationarity, resulting in a huge amount of computation time. In this study, we use a non-random patch mask that passes through only one limited region in addition to an improved random mask to reduce the number of masks needed, thereby speeding up the RISE process.