BIROn - Birkbeck Institutional Research Online

    Saliency propagation from simple to difficult

    Gong, C. and Tao, D. and Wei, L. and Maybank, Stephen J. and Meng, F. and Fu, K. and Yang, Jie (2015) Saliency propagation from simple to difficult. IEEE Computer Society Conference on Computer Vision and Pattern Recognition , pp. 2531-2539. ISSN 1063-6919.

    [img]
    Preview
    Text
    15472.pdf - Author's Accepted Manuscript

    Download (1MB) | Preview

    Abstract

    Saliency propagation has been widely adopted for identifying the most attractive object in an image. The propagation sequence generated by existing saliency detection methods is governed by the spatial relationships of image regions, i.e., the saliency value is transmitted between two adjacent regions. However, for the inhomogeneous difficult adjacent regions, such a sequence may incur wrong propagations. In this paper, we attempt to manipulate the propagation sequence for optimizing the propagation quality. Intuitively, we postpone the propagations to difficult regions and meanwhile advance the propagations to less ambiguous simple regions. Inspired by the theoretical results in educational psychology, a novel propagation algorithm employing the teaching-to-learn and learning-to-teach strategies is proposed to explicitly improve the propagation quality. In the teaching-to-learn step, a teacher is designed to arrange the regions from simple to difficult and then assign the simplest regions to the learner. In the learning-to-teach step, the learner delivers its learning confidence to the teacher to assist the teacher to choose the subsequent simple regions. Due to the interactions between the teacher and learner, the uncertainty of original difficult regions is gradually reduced, yielding manifest salient objects with optimized background suppression. Extensive experimental results on benchmark saliency datasets demonstrate the superiority of the proposed algorithm over twelve representative saliency detectors.

    Metadata

    Item Type: Article
    Additional Information: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, U.S., 7-12 Jun 2015 - (c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Depositing User: Administrator
    Date Deposited: 09 Jun 2016 12:23
    Last Modified: 09 Aug 2023 12:38
    URI: https://eprints.bbk.ac.uk/id/eprint/15472

    Statistics

    Activity Overview
    6 month trend
    373Downloads
    6 month trend
    189Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item