Concept Guided Co-salient Object Detection

TL;DR

This paper introduces ConceptCoSOD, a novel framework that leverages high-level semantic concepts extracted from text to improve co-salient object detection across images, especially under challenging conditions.

Contribution

It proposes a concept-guided approach with a resampling strategy for better semantic prior extraction, significantly enhancing detection accuracy and robustness.

Findings

Outperforms existing methods on benchmark datasets

Achieves higher accuracy in challenging visual conditions

Demonstrates strong generalization across corrupted settings

Abstract

Co-salient object detection (Co-SOD) aims to identify common salient objects across a group of related images. While recent methods have made notable progress, they typically rely on low-level visual patterns and lack semantic priors, limiting their detection performance. We propose ConceptCoSOD, a concept-guided framework that introduces high-level semantic knowledge to enhance co-saliency detection. By extracting shared text-based concepts from the input image group, ConceptCoSOD provides semantic guidance that anchors the detection process. To further improve concept quality, we analyze the effect of diffusion timesteps and design a resampling strategy that selects more informative steps for learning robust concepts. This semantic prior, combined with the resampling-enhanced representation, enables accurate and consistent segmentation even in challenging visual conditions. Extensive experiments on three benchmark datasets and five corrupted settings demonstrate that ConceptCoSOD significantly outperforms existing methods in both accuracy and generalization.