Zero-Shot Co-salient Object Detection Framework
This addresses the need for training-free CoSOD methods in computer vision, offering a novel approach but with incremental improvements over recent supervised techniques.
The paper tackles the problem of Co-salient Object Detection (CoSOD) without training by introducing the first zero-shot framework, which outperforms existing unsupervised methods and some fully supervised methods, achieving competitive results on standard datasets.
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.