elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

End-to-End Saliency Mapping via Probability Distribution Prediction

Jetley, Saumya and Murray, Naila and Vig, Eleonora (2016) End-to-End Saliency Mapping via Probability Distribution Prediction. In: Proceedings of Computer Vision and Pattern Recognition 2016, pp. 5753-5761. IEEE Xplore. Conference on Computer Vision and Pattern Recognition 2016, 27-30 June 2016, Las Vegas, USA.

[img] PDF
1MB

Official URL: http://cvpr2016.thecvf.com/program/news_updates#proceedings

Abstract

Most saliency estimation methods aim to explicitly model low-level conspicuity cues such as edges or blobs and may additionally incorporate top-down cues using face or text detection. Data-driven methods for training saliency mod- els using eye-fixation data are increasingly popular, par- ticularly with the introduction of large-scale datasets and deep architectures. However, current methods in this lat- ter paradigm use loss functions designed for classification or regression tasks whereas saliency estimation is evalu- ated on topographical maps. In this work, we introduce a new saliency map model which formulates a map as a generalized Bernoulli distribution. We then train a deep ar- chitecture to predict such maps using novel loss functions which pair the softmax activation function with measures designed to compute distances between probability distri- butions. We show in extensive experiments the effective- ness of such loss functions over standard ones on four pub- lic benchmark datasets, and demonstrate improved perfor- mance over state-of-the-art saliency methods.

Item URL in elib:https://elib.dlr.de/105153/
Document Type:Conference or Workshop Item (Poster)
Title:End-to-End Saliency Mapping via Probability Distribution Prediction
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Jetley, Saumyasjetley (at) robots.ox.ac.ukUNSPECIFIED
Murray, Nailanaila.murray (at) xrce.xerox.comUNSPECIFIED
Vig, Eleonoraeleonora.vig (at) dlr.deUNSPECIFIED
Date:2016
Journal or Publication Title:Proceedings of Computer Vision and Pattern Recognition 2016
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 5753-5761
Publisher:IEEE Xplore
Status:Published
Keywords:End-to-End Saliency Mapping
Event Title:Conference on Computer Vision and Pattern Recognition 2016
Event Location:Las Vegas, USA
Event Type:international Conference
Event Dates:27-30 June 2016
Organizer:IEEE Computer Society and the Computer Vision Foundation (CVF)
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - Vabene++ (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By:INVALID USER
Deposited On:20 Jul 2016 10:52
Last Modified:31 Jul 2019 20:02

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.