Publication Type

Journal Article

Version

publishedVersion

Publication Date

12-2015

Abstract

Existing computational models for salient object detection primarily rely on hand-crafted features, which are only able to capture low-level contrast information. In this paper, we learn the hierarchical contrast features by formulating salient object detection as a binary labeling problem using deep learning techniques. A novel superpixelwise convolutional neural network approach, called SuperCNN, is proposed to learn the internal representations of saliency in an efficient manner. In contrast to the classical convolutional networks, SuperCNN has four main properties. First, the proposed method is able to learn the hierarchical contrast features, as it is fed by two meaningful superpixel sequences, which is much more effective for detecting salient regions than feeding raw image pixels. Second, as SuperCNN recovers the contextual information among superpixels, it enables large context to be involved in the analysis efficiently. Third, benefiting from the superpixelwise mechanism, the required number of predictions for a densely labeled map is hugely reduced. Fourth, saliency can be detected independent of region size by utilizing a multiscale network structure. Experiments show that SuperCNN can robustly detect salient objects and outperforms the state-of-the-art methods on three benchmark datasets. © 2015, Springer Science+Business Media New York.

Keywords

Contextual information, Convolutional neural network, Deep learning, Feature learning, Internal representation, Saliency detection, Salient object detection, State-of-the-art methods

Discipline

Databases and Information Systems

Research Areas

Information Systems and Management

Publication

International Journal of Computer Vision

Volume

115

Issue

3

First Page

330

Last Page

344

ISSN

0920-5691

Identifier

10.1007/s11263-015-0822-0

Publisher

Springer

Additional URL

https://doi.org/10.1007/s11263-015-0822-0

Download

Share

COinS