Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: HyperFusion-Net: hyper-densely reflective feature fusion for salient object detection
Author: Zhang, P.
Liu, W.
Lei, Y.
Lu, H.
Citation: Pattern Recognition, 2019; 93:521-533
Publisher: Elsevier
Issue Date: 2019
ISSN: 0031-3203
Statement of
Pingping Zhang, Wei Liu, Yinjie Lei, Huchuan Lu
Abstract: Salient Object Detection (SOD), which aims to find the most important region of interest and segment the relevant objects/items in that region, is an important yet challenging task in computer vision and image processing. This vision problem is inspired by the fact that human perceives the main scene elements with high priorities. Thus, accurate detection of salient objects in complex scenes is critical for human-computer interaction. In this paper, we present a novel reflective feature learning framework, which results in high detection accuracy while maintaining a compact model design. The proposed framework utilizes a hyper-densely reflective feature fusion network (named HyperFusion-Net) to automatically predict the most important area and segment the associated objects in an end-to-end manner. Specifically, inspired by the human perception system and image reflection separation, we first decompose the input images into reflective image pairs by content-preserving transforms. Then, the complementary information of reflective image pairs is jointly extracted by an Interweaved Convolutional Neural Network (ICNN) and hierarchically combined with a hyper-dense fusion mechanism. Based on the fused multi-scale features, our method finally achieves a promising way of predicting salient objects, in which we cast the SOD as a pixel-wise classification problem. Extensive experiments on seven public datasets demonstrate that the proposed method consistently outperforms other state-of-the-art methods with a large margin.
Keywords: Salient object detection; image reflection separation; mulitple feature fusion; Convolutional Neural Network
Rights: ©2019 Elsevier Ltd. All rights reserved.
RMID: 0030116993
DOI: 10.1016/j.patcog.2019.05.012
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.