Global-and-Local Collaborative Learning for Co-Salient Object Detection

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

16 Scopus Citations
View graph of relations


  • Runmin Cong
  • Ning Yang
  • Chongyi Li
  • Huazhu Fu
  • Yao Zhao
  • Qingming Huang


Original languageEnglish
Pages (from-to)1920-1931
Journal / PublicationIEEE Transactions on Cybernetics
Issue number3
Online published22 Jul 2022
Publication statusPublished - Mar 2023


The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effectively extract interimage correspondence is crucial for the CoSOD task. In this article, we propose a global-and-local collaborative learning (GLNet) architecture, which includes a global correspondence modeling (GCM) and a local correspondence modeling (LCM) to capture the comprehensive interimage corresponding relationship among different images from the global and local perspectives. First, we treat different images as different time slices and use 3-D convolution to integrate all intrafeatures intuitively, which can more fully extract the global group semantics. Second, we design a pairwise correlation transformation (PCT) to explore similarity correspondence between pairwise images and combine the multiple local pairwise correspondences to generate the local interimage relationship. Third, the interimage relationships of the GCM and LCM are integrated through a global-and-local correspondence aggregation (GLA) module to explore more comprehensive interimage collaboration cues. Finally, the intra and inter features are adaptively integrated by an intra-and-inter weighting fusion (AEWF) module to learn co-saliency features and predict the co-saliency map. The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that our model trained on a small dataset (about 3k images) still outperforms 11 state-of-the-art competitors trained on some large datasets (about 8k–200k images).

Research Area(s)

  • Semantics, Task analysis, Feature extraction, Convolution, Object detection, Computational modeling, Collaborative work, 3-D convolution, co-salient object detection (CoSOD), global correspondence modeling (GCM), local correspondence modeling (LCM), NETWORK, DENSE

Citation Format(s)

Global-and-Local Collaborative Learning for Co-Salient Object Detection. / Cong, Runmin; Yang, Ning; Li, Chongyi et al.
In: IEEE Transactions on Cybernetics, Vol. 53, No. 3, 03.2023, p. 1920-1931.

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