Improvement of U-Net architecture for image binarization with activation functions replacement

Alexander V. Gayer; Alexander V. Sheshkus; Dmitri P. Nikolaev; Vladimir V. Arlazarov

doi:10.1117/12.2587027

4 January 2021 Improvement of U-Net architecture for image binarization with activation functions replacement

Alexander V. Gayer, Alexander V. Sheshkus, Dmitri P. Nikolaev, Vladimir V. Arlazarov

Proceedings Volume 11605, Thirteenth International Conference on Machine Vision; 116050Y (2021) https://doi.org/10.1117/12.2587027
Event: Thirteenth International Conference on Machine Vision, 2020, Rome, Italy

Abstract

In this work we study the effect of activation functions in a neural network. We consider how activation functions with different properties and their combination affect the final quality of the model. Due to optimization and speed performance issues with most of bounded functions that are represented by sigmoids, we propose the generalized version of SoftSign function - ratio function (rf). Its shape greatly depends on introduced degree parameter, which in theory leads to new interesting property - contraction to zero. For evaluation, we chose image binarization problem: based on UNet architecture of DIBCO-2017 winners, we conducted all experiments with replacing activation functions only. Our research has led us to the state-of-the-art results in binarization quality on DIBCO-2017 test dataset. U-Net with modified activation functions significantly outperforms all existing solutions in all metrics.

Citation Download Citation

Alexander V. Gayer, Alexander V. Sheshkus, Dmitri P. Nikolaev, and Vladimir V. Arlazarov "Improvement of U-Net architecture for image binarization with activation functions replacement", Proc. SPIE 11605, Thirteenth International Conference on Machine Vision, 116050Y (4 January 2021); https://doi.org/10.1117/12.2587027

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