Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Shallow and deep convolutional networks for saliency prediction

Pan, Junting, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477, Sayrol, Elisa, O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 and Giró-i-Nieto, Xavier orcid logoORCID: 0000-0002-9935-5332 (2016) Shallow and deep convolutional networks for saliency prediction. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 26 Jun 2016, Las Vegas, NV..

Abstract
The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles. This paper, however, addresses the problem with a completely data-driven approach by training a convolutional neural network (convnet). The learning process is formulated as a minimization of a loss function that measures the Euclidean distance of the predicted saliency map with the provided ground truth. The recent publication of large datasets of saliency prediction has provided enough data to train end-to-end architectures that are both fast and accurate. Two designs are proposed: a shallow convnet trained from scratch, and a another deeper solution whose first three layers are adapted from another network trained for classification. To the authors knowledge, these are the first end-to-end CNNs trained and tested for the purpose of saliency prediction.
Metadata
Item Type:Conference or Workshop Item (Poster)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:computer vision; saliency prediction
Subjects:Computer Science > Machine learning
Computer Science > Image processing
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Publisher:IEEE
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland SFI/12/RC/2289
ID Code:21206
Deposited On:22 Jun 2016 10:51 by Kevin Mcguinness . Last Modified 25 Jan 2019 09:35
Documents

Full text available as:

[thumbnail of Arxiv version of paper]
Preview
PDF (Arxiv version of paper) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
419kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record