TY - JOUR AU - Nguyen, Hoang D. AU - Vu, Xuan-Son AU - Le, Duc-Trong PY - 2021/05/18 Y2 - 2024/03/29 TI - Modular Graph Transformer Networks for Multi-Label Image Classification JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 10 SE - AAAI Technical Track on Machine Learning III DO - 10.1609/aaai.v35i10.17098 UR - https://ojs.aaai.org/index.php/AAAI/article/view/17098 SP - 9092-9100 AB - 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 https://github.com/ReML-AI/MGTN. ER -