Engaging Part-whole Hierarchies and Contrast Cues for Salient Object Detection

Qiang Zhang, Mingxing Duanmu, Yongjiang Luo, Yi Liu, Jungong Han

Research output: Contribution to journalArticlepeer-review

11 Citations (SciVal)
68 Downloads (Pure)

Abstract

Real-world scenes always exhibit objects with clutter backgrounds, posing great challenges for deep salient object detection models. In this paper, we propose salient object detection by engaging two saliency cues, i.e., the part-whole hierarchies and contrast cues, resulting in a PWHCNet. Specifically, two branches, which consists of a Dynamic Grouping Capsules (DGC) branch and a DenseHRNet branch, are put in place to learn the part-whole hierarchies and contrast cues, respectively. Moreover, to help highlight the whole salient object in complex scenes, a Background Suppression (BS) module is proposed to guide the shallow features of DenseHRNet with the aid of the part-whole relational cues captured by DGC. Subsequently, these two saliency cues are integrated via a Self-Channel and Mutual-Spatial (SCMS) attention mechanism. Experimental results on five benchmarks demonstrate that the proposed PWHCNet achieves state-of-the-art performance while obtaining the whole salient objects with fine details.

Original languageEnglish
Pages (from-to)3644-3658
Number of pages15
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume32
Issue number6
Early online date16 Aug 2021
DOIs
Publication statusPublished - 01 Jun 2022

Keywords

  • Object detection
  • Feature extraction
  • Routing
  • Noise measurement
  • Semantics
  • Saliency detection
  • Image segmentation
  • Salient object detection
  • part-whole hierarchies
  • contrast
  • attention
  • REPRESENTATION
  • FRAMEWORK
  • IMAGE
  • MODEL

Fingerprint

Dive into the research topics of 'Engaging Part-whole Hierarchies and Contrast Cues for Salient Object Detection'. Together they form a unique fingerprint.

Cite this