首页|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
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
Spie-Int Soc Optical Engineering
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。
image recognitionvisualizationRISE
Tomoki Nakada、Kousuke Imamura
展开 >
Kanazawa University, Kakuma-machi, Kanazawa, Ishikawa, 920-1192 Japan
International Workshop on Advanced Imaging Technology
Jeju(KR)
International Workshop on Advanced Imaging Technology
NETL
Spie-Int Soc Optical Engineering
