Co-saliency detection with intra-group two-stage group semantics propagation and inter-group contrastive learning

Co-salient object detection (CoSOD) aims at discovering the salient objects with repeatability from multiple relevant images and suppressing non-repetitively appearing salient and non-salient ones. Recently, learning-based methods have shown the advantages in the CoSOD tasks. However, modeling the intra-group semantics and suppressing the inter-group noise objects are still two challenges. In this paper, we propose a unified Two-stage grOup semantics PropagatIon and Contrastive learning NETwork (TopicNet) for CoSOD. TopicNet consists of an intra-group two-stage group semantics propagation module (TGSP) and an inter-group contrastive learning module (CLM). On one hand, in the first stage of TGSP, we put forward an image-to-group propagation module (IGP) to capture the interimage similarity feature interactions. In the second stage of TGSP, a group-to-pixel propagation module (GPP) is designed to construct the connection between inter-image interactions and inter-pixel correspondences to distill consensus representation. GPP redistributes the interactions with different attention weights to each pixel so as to improve the robustness of group semantics. On the other hand, in CLM, using the design of positive samples enhances the semantic consistency of group semantics. Using the design of negative samples explores the interactive suppression relationships of co-salient objects and noise objects, which suppresses non-repetitively appearing salient and non-salient objects. TGSP and CLM are jointly integrated into an end-to-end unified network predicting the co-salient objects. Experimental results on three prevailing benchmarks reveal that TopicNet outperforms other competitors under various evaluation metrics.