Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation

04/01/2021
by   Rongjie Li, et al.
25

Scene graph generation is an important visual understanding task with a broad range of vision applications. Despite recent tremendous progress, it remains challenging due to the intrinsic long-tailed class distribution and large intra-class variation. To address these issues, we introduce a novel confidence-aware bipartite graph neural network with adaptive message propagation mechanism for unbiased scene graph generation. In addition, we propose an efficient bi-level data resampling strategy to alleviate the imbalanced data distribution problem in training our graph network. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including Visual Genome, Open Images V4/V6, demonstrating its effectiveness and generality.

READ FULL TEXT

page 1

page 12

page 14

research
08/15/2022

CAME: Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation

The scene graph generation has gained tremendous progress in recent year...
research
11/09/2018

Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks

We introduce a new scene graph generation method called image-level atte...
research
01/01/2023

Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation

An unbiased scene graph generation (SGG) algorithm referred to as Skew C...
research
04/03/2023

Unbiased Scene Graph Generation in Videos

The task of dynamic scene graph generation (SGG) from videos is complica...
research
07/27/2022

Iterative Scene Graph Generation

The task of scene graph generation entails identifying object entities a...
research
06/29/2018

Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation

Generating scene graph to describe all the relations inside an image gai...
research
12/10/2021

Neural Belief Propagation for Scene Graph Generation

Scene graph generation aims to interpret an input image by explicitly mo...

Please sign up or login with your details

Forgot password? Click here to reset