S^3Net: Self-supervised self-ensembling network for semi-supervised RGB-D salient object detection

Lei Zhu, Xiaoqiang Wang, Ping Li, Xin Yang, Qing Zhang, Weiming Wang, Carola Bibiane Schonlieb, C. L. Philip Chen

Research output: Journal article publicationJournal articleAcademic researchpeer-review

3 Citations (Scopus)

Abstract

RGB-D salient object detection aims to detect visually distinctive objects or regions from a pair of the RGB image and the depth image. State-of-the-art RGB-D saliency detectors are mainly based on convolutional neural networks but almost suffer from an intrinsic limitation relying on the labeled data, thus degrading detection accuracy in complex cases. In this work, we present a self-supervised self-ensembling network (S<formula><tex>$^3$</tex></formula>Net) for semi-supervised RGB-D salient object detection by leveraging the unlabeled data and exploring a self-supervised learning mechanism. To be specific, we first build a self-guided convolutional neural network (SG-CNN) as a baseline model by developing a series of three-layer cross-model feature fusion (TCF) modules to leverage complementary information among depth and RGB modalities and formulating an auxiliary task that predicts a self-supervised image rotation angle. After that, to further explore the knowledge from unlabeled data, we assign SG-CNN to a student network and a teacher network, and encourage the saliency predictions and self-supervised rotation predictions from these two networks to be consistent on the unlabeled data. Experimental results on seven widely-used benchmark datasets demonstrate that our network quantitatively and qualitatively outperforms the state-of-the-art methods.

Original languageEnglish
Pages (from-to)1-14
Number of pages14
JournalIEEE Transactions on Multimedia
DOIs
Publication statusAccepted/In press - Nov 2021

Keywords

  • and cross-model and cross-level feature aggregation
  • Convolutional neural networks
  • Detectors
  • Feature extraction
  • Object detection
  • RGB-D salient object detection
  • Saliency detection
  • self-supervised learning
  • semi-supervised learning
  • Task analysis
  • Training

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'S^3Net: Self-supervised self-ensembling network for semi-supervised RGB-D salient object detection'. Together they form a unique fingerprint.

Cite this