BROWSE
Detail
Conference Paper
Unbiased Heterogeneous Scene Graph Generation with Relation-Aware Message Passing Neural Network
Cited 12 time in 
Share 
Share
- Authors
- Kanghoon Yoon, Kibum Kim, Jinyoung Moon, Chanyoung Park
- Issue Date
- 2023-02
- Citation
- The Association for the Advancement of Artificial Intelligence Conference on Artificial Intelligence (AAAI) 2023, pp.3285-3294
- Language
- English
- Type
- Conference Paper
- Abstract
- Recent scene graph generation (SGG) frameworks have focused on learning complex relationships among multiple objects in an image. Thanks to the nature of the message passing neural network (MPNN) that models high-order interactions between objects and their neighboring objects, they are dominant representation learning modules for SGG. However, existing MPNN-based frameworks assume the scene graph as a homogeneous graph, which restricts the context-awareness of visual relations between objects. That is, they overlook the fact that the relations tend to be highly dependent on the objects with which the relations are associated. In this paper, we propose an unbiased heterogeneous scene graph generation (HetSGG) framework that captures relation-aware context using message passing neural networks. We devise a novel message passing layer, called relation-aware message passing neural network (RMP), that aggregates the contextual information of an image considering the predicate type between objects. Our extensive evaluations demonstrate that HetSGG outperforms state-of-the-art methods, especially outperforming on tail predicate classes. The source code for HetSGG is available at https://github.com/KanghoonYoon/hetsgg-torch
- KSP Keywords
- Context awareness, Contextual information, Learning modules, Message Passing, Multiple objects, Representation learning, Scene graph, Source Code, graph generation, high order, neural network