arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.00549cs.CV

TF-SSD: 通过协同掩码过滤实现的强管道用于无训练共显著物体检测

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

XJTLU（西交利物浦大学）；University of Liverpool（利物浦大学）；China University of Petroleum (East China)（中国石油大学（华东））；Nanjing University of Information Science and Technology（南京信息工程大学）

Zhijin He, Shuo Jin, Siyue Yu, Shuwei Wu, Bingfeng Zhang, Li Yu, Jimin Xiao

备注：
Accepted by CVPR26
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出TF-SSD，通过SAM和DINO的协同作用，利用视觉基础模型进行无训练共显著物体检测，通过掩码过滤提升检测性能，实验显示优于现有方法。

摘要：

共显著物体检测（CoSOD）旨在分割在一组相关图像中一致出现的显著物体。尽管最近基于训练的方法取得了显著进展，但它们仍受限于闭集数据集并表现出有限的泛化能力。然而，很少有研究探索视觉基础模型（VFMs）在解决CoSOD中的潜力，这些模型表现出强大的泛化能力和稳健的显著性理解。本文研究并利用VFMs进行CoSOD，并进一步提出一种新的无训练方法TF-SSD，通过SAM和DINO的协同作用。具体来说，我们首先利用SAM生成全面的原始建议，这些建议作为候选掩码池。然后，我们引入一个质量掩码生成器来过滤冗余掩码，从而获得一个精炼的掩码集。由于该生成器基于SAM，它本质上缺乏对显著性的语义理解。为此，我们采用一种图像内显著性过滤器，利用DINO的注意力图来识别单个图像内的视觉显著掩码。此外，为了扩展跨图像的显著性理解，我们提出一种跨图像原型选择器，计算跨图像原型之间的相似度分数以选择得分最高的掩码。这些选定的掩码作为CoSOD的最终预测。大量实验表明，我们的TF-SSD在现有方法（例如，比最近的无训练方法高出13.7%）上表现更优。代码可在https://github.com/hzz-yy/TF-SSD上获取。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑