Reducing the number of masks to accelerate the neural network visualization of RISE

Tomoki Nakada; Kousuke Imamura

doi:10.1117/12.2666680

25 March 2023 Reducing the number of masks to accelerate the neural network visualization of RISE

Tomoki Nakada, Kousuke Imamura

Proceedings Volume 12592, International Workshop on Advanced Imaging Technology (IWAIT) 2023; 125921I (2023) https://doi.org/10.1117/12.2666680
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2023, 2023, Jeju, Korea, Republic of

Abstract

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.

Citation Download Citation

Tomoki Nakada and Kousuke Imamura "Reducing the number of masks to accelerate the neural network visualization of RISE", Proc. SPIE 12592, International Workshop on Advanced Imaging Technology (IWAIT) 2023, 125921I (25 March 2023); https://doi.org/10.1117/12.2666680

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available