RGB-D salient object detection via deep fusion of semantics and details

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Shimin Zhao
  • Miaomiao Chen
  • Pengjie Wang
  • Ying Cao
  • Pingping Zhang
  • And 1 others
  • Xin Yang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article numbere1954
Journal / PublicationComputer Animation and Virtual Worlds
Volume31
Issue number4-5
Publication statusPublished - Jul 2020

Abstract

In this paper, we address RGB-D salient object detection task by jointly leveraging semantics and contour details of salient objects. We propose a novel semantics-and-details complementary fusion network to adaptively integrate cross-model and multilevel features. Specifically, we employ two kinds of fusion modules in our model, which are designed for fusing high-level semantic features and integrating contour detail features of the scene components, respectively. The semantics fusion module aggregates high-level interdependent semantic relationships by a nonlinear weighted summation of small and medium receptive fields. Meanwhile, the details module integrates multi-level contour detail features to leverage expressive details of salient objects. We achieve new state-of-the-art salient object detection results on seven RGB-D datasets, that is, STERE, NJU2000, LFSD, NLPR, SSD, DES, and SIP2019 dataset. Experimental results demonstrate that our method outperforms eleven state-of-the-art salient object detection methods.

Research Area(s)

  • cross-model and multilevel features, feature fusion and deep fusion, RGB-D, salient object detection

Citation Format(s)

RGB-D salient object detection via deep fusion of semantics and details. / Zhao, Shimin; Chen, Miaomiao; Wang, Pengjie; Cao, Ying; Zhang, Pingping; Yang, Xin.

In: Computer Animation and Virtual Worlds, Vol. 31, No. 4-5, e1954, 07.2020.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review