Modular Graph Transformer Networks for Multi-Label Image Classification

Nguyen, H. D. , Vu, X.-S. and Le, D.-T. (2021) Modular Graph Transformer Networks for Multi-Label Image Classification. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, 02-09 Feb 2021, pp. 9092-9100. ISBN 9781577358664

Full text not currently available from Enlighten.

Publisher's URL:


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. The proposed 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 multi-label image classification. The source code is available at

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Nguyen, Dr Hoang D.
Authors: Nguyen, H. D., Vu, X.-S., and Le, D.-T.
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record