Zero-Shot Co-salient Object Detection Framework

TL;DR

This paper presents the first zero-shot co-salient object detection framework that leverages foundational vision models without training, introducing novel modules and outperforming many existing methods.

Contribution

It introduces a training-free zero-shot CoSOD framework with novel group prompt and co-saliency map modules, outperforming prior unsupervised and some supervised methods.

Findings

Outperforms existing unsupervised CoSOD methods.

Surpasses some fully supervised methods before 2020.

Remains competitive with recent supervised approaches.

Abstract

Co-salient Object Detection (CoSOD) endeavors to replicate the human visual system's capacity to recognize common and salient objects within a collection of images. Despite recent advancements in deep learning models, these models still rely on training with well-annotated CoSOD datasets. The exploration of training-free zero-shot CoSOD frameworks has been limited. In this paper, taking inspiration from the zero-shot transfer capabilities of foundational computer vision models, we introduce the first zero-shot CoSOD framework that harnesses these models without any training process. To achieve this, we introduce two novel components in our proposed framework: the group prompt generation (GPG) module and the co-saliency map generation (CMP) module. We evaluate the framework's performance on widely-used datasets and observe impressive results. Our approach surpasses existing unsupervised methods and even outperforms fully supervised methods developed before 2020, while remaining competitive with some fully supervised methods developed before 2022.