Multiscale fully convolutional network for image saliency

Simone Bianco; Marco Buzzelli; Raimondo Schettini

doi:10.1117/1.JEI.27.5.051221

12 May 2018 Multiscale fully convolutional network for image saliency

Simone Bianco, Marco Buzzelli, Raimondo Schettini

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 5, 051221 (May 2018). https://doi.org/10.1117/1.JEI.27.5.051221

Abstract

We focus on saliency estimation in digital images. We describe why it is important to adopt a data-driven model for such an illposed problem, allowing for a universal concept of “saliency” to naturally emerge from data that are typically annotated with drastically heterogeneous criteria. Our learning-based method also involves an explicit analysis of the input at multiple scales, in order to take into account images of different resolutions, depicting subjects of different sizes. Furthermore, despite training our model on binary ground truths only, we are able to output a continuous-valued confidence map, which represents the probability of each image pixel being salient. Every contribution of our method for saliency estimation is singularly tested according to a standard evaluation benchmark, and our final proposal proves to be very effective in a comparison with the state-of-the-art.

Citation Download Citation

Simone Bianco, Marco Buzzelli, and Raimondo Schettini "Multiscale fully convolutional network for image saliency," Journal of Electronic Imaging 27(5), 051221 (12 May 2018). https://doi.org/10.1117/1.JEI.27.5.051221

Received: 15 January 2018; Accepted: 20 April 2018; Published: 12 May 2018

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