Group attention retention network for co-salient object detection

The co-salient object detection (Co-SOD) aims to discover common, salient objects from a group of images. With the development of convolutional neural networks, the performance of Co-SOD methods has been significantly improved. However, some models cannot construct collaborative relationships across...

Full description

Saved in:
Bibliographic Details
Published inMachine vision and applications Vol. 34; no. 6; p. 107
Main Authors Liu, Jing, Wang, Jiaxiang, Fan, Zhiwei, Yuan, Min, Wang, Weikang, Yu, Jiexiao
Format Journal Article
LanguageEnglish
Published Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2023
Springer Nature B.V
Subjects
Artificial neural networks
Collaboration
Communications Engineering
Computer Science
Decoding
Garnets
Image Processing and Computer Vision
Modules
Networks
Object recognition
Original Paper
Pattern Recognition
Retention
Salience
Source code
Vision systems
Vision transformer
Attention retention
Co-salient object detection
Group attention
Online AccessGet full text

Cover

More Information
Summary:The co-salient object detection (Co-SOD) aims to discover common, salient objects from a group of images. With the development of convolutional neural networks, the performance of Co-SOD methods has been significantly improved. However, some models cannot construct collaborative relationships across images optimally and lack effective retention of collaborative features in the top-down decoding process. In this paper, we propose a novel group attention retention network (GARNet), which captures excellent collaborative features and retains them. First, a group attention module is designed to construct the inter-image relationships. Second, an attention retention module and a spatial attention module are designed to retain inter-image relationships for protecting them from being diluted and filter out the cluttered context during feature fusion, respectively. Finally, considering the intra-group consistency and inter-group separability of images, an embedding loss is additionally designed to discriminate between real collaborative objects and distracting objects. The experiments on four datasets (iCoSeg, CoSal2015, CoSoD3k, and CoCA) show that our GARNet outperforms previous state-of-the-art methods. The source code is available at https://github.com/TJUMMG/GARNet .
ISSN:0932-8092
1432-1769
DOI:10.1007/s00138-023-01462-7