Search: onr:"swepub:oai:DiVA.org:umu-196096" >
Modular Graph Trans...
Modular Graph Transformer Networks for Multi-Label Image Classification
-
- Nguyen, Hoang D. (author)
- School of Computing Science, University of Glasgow, Singapore, Singapore
-
- Vu, Xuan-Son, 1988- (author)
- Umeå universitet,Institutionen för datavetenskap
-
- Le, Duc-Trong (author)
- University of Engineering and Technology, Vietnam National University, Viet Nam
-
(creator_code:org_t)
- Association for the Advancement of Artificial Intelligence, 2021
- 2021
- English.
-
In: 35th AAAI Conference on Artificial Intelligence, AAAI 2021, 33 Conference on Innovative Applications of Artificial Intelligence and the 11 Symposium on Educational Advances in Artificial Intelligence. - : Association for the Advancement of Artificial Intelligence. - 9781713835974 - 9781577358664 ; , s. 9092-9100
- Related links:
-
https://ojs.aaai.org...
-
show more...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- With the recent advances in graph neural networks, there is a rising number of studies on graph-based multi-label classification with the consideration of object dependencies within visual data. Nevertheless, graph representations can become indistinguishable due to the complex nature of label relationships. We propose a multi-label image classification framework based on graph transformer networks to fully exploit inter-label interactions. The paper presents a modular learning scheme to enhance the classification performance by segregating the computational graph into multiple sub-graphs based on modularity. Our approach, named Modular Graph Transformer Networks (MGTN), is capable of employing multiple backbones for better information propagation over different sub-graphs guided by graph transformers and convolutions. We validate our framework on MS-COCO and Fashion550K datasets to demonstrate improvements for multilabel image classification. The source code is available at https://github.com/ReML-AI/MGTN.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database