Zero-Shot Co-Salient Object Detection Framework

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 e...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 4010 - 4014
Main Authors Xiao, Haoke, Tang, Lv, Li, Bo, Luo, Zhiming, Li, Shaozi
Format Conference Proceeding
LanguageEnglish
Published IEEE 14.04.2024
Subjects
Computational modeling
Computer vision
Foundational Computer Vision Model
Image recognition
Object detection
Signal processing
Training
Visualization
Zero-shot Co-saliency Detection
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10448084