Evaluation of bottom-up saliency model using deep features pretrained by deep convolutional neural networks

Ali Mahdi; Jun Qin

doi:10.1117/1.JEI.28.3.033033

25 June 2019 Evaluation of bottom-up saliency model using deep features pretrained by deep convolutional neural networks

Ali Mahdi, Jun Qin

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 3, 033033 (June 2019). https://doi.org/10.1117/1.JEI.28.3.033033

Abstract

We present extensive evaluations of deep features pretrained by state-of-the-art deep convolutional neural networks (DCNNs) for predictions of human fixations. The evaluations are conducted using a bottom-up saliency model, which utilizes deep features of DCNNs pretrained for object classification. Using various selections of deep feature maps, 35 implementations of the bottom-up saliency model are computed, evaluated, and compared over three publicly available datasets using four evaluation metrics. The experimental results demonstrate that the pretrained deep features are strong predictors of human fixations. The incorporation of multiscale deep feature maps benefits the saliency prediction. The depth of DCNNs has a negative effect on saliency prediction. Moreover, we also compare the performance of the proposed deep features-based bottom-up saliency model with the other eight bottom-up saliency models. The comparison results show that our saliency model can outperform other conventional bottom-up saliency models.

Citation Download Citation

Ali Mahdi and Jun Qin "Evaluation of bottom-up saliency model using deep features pretrained by deep convolutional neural networks," Journal of Electronic Imaging 28(3), 033033 (25 June 2019). https://doi.org/10.1117/1.JEI.28.3.033033

Received: 4 March 2019; Accepted: 3 June 2019; Published: 25 June 2019

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