TF-SSD: A Strong Pipeline via Synergic Mask Filter for Training-free Co-salient Object Detection

2026-04-01

AI Summary

This work addresses the limitations of existing co-salient object detection (CoSOD) methods, which often rely on training and suffer from restricted generalization. To overcome these issues, we propose the first training-free CoSOD framework that synergistically leverages two foundational vision models: SAM and DINO. Our approach employs SAM to generate high-quality candidate masks and utilizes DINO’s attention maps to construct an intra-image saliency filter. Furthermore, we introduce a cross-image prototype selection mechanism to accurately identify co-salient objects. Extensive experiments demonstrate that the proposed method significantly outperforms current state-of-the-art techniques across multiple benchmarks, achieving a 13.7% improvement over the latest training-free approach while exhibiting superior generalization capability and detection accuracy.

Abstract

Co-salient Object Detection (CoSOD) aims to segment salient objects that consistently appear across a group of related images. Despite the notable progress achieved by recent training-based approaches, they still remain constrained by the closed-set datasets and exhibit limited generalization. However, few studies explore the potential of Vision Foundation Models (VFMs) to address CoSOD, which demonstrate a strong generalized ability and robust saliency understanding. In this paper, we investigate and leverage VFMs for CoSOD, and further propose a novel training-free method, TF-SSD, through the synergy between SAM and DINO. Specifically, we first utilize SAM to generate comprehensive raw proposals, which serve as a candidate mask pool. Then, we introduce a quality mask generator to filter out redundant masks, thereby acquiring a refined mask set. Since this generator is built upon SAM, it inherently lacks semantic understanding of saliency. To this end, we adopt an intra-image saliency filter that employs DINO's attention maps to identify visually salient masks within individual images. Moreover, to extend saliency understanding across group images, we propose an inter-image prototype selector, which computes similarity scores among cross-image prototypes to select masks with the highest score. These selected masks serve as final predictions for CoSOD. Extensive experiments show that our TF-SSD outperforms existing methods (e.g., 13.7\% gains over the recent training-free method). Codes are available at https://github.com/hzz-yy/TF-SSD.

Problem

• Co-salient Object Detection
• Vision Foundation Models
• Generalization
• Training-free
• Saliency Understanding

Innovation

• Training-free
• Co-salient Object Detection
• Vision Foundation Models
• SAM-DINO Synergy
• Mask Filtering