Scene Graph Generation with External Knowledge and Image Reconstruction

Abstract

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and relationship labels, or often come with noisy and missing annotations, which makes the development of a reliable scene graph prediction model very challenging. In this paper, we propose a novel scene graph generation algorithm with external knowledge and image reconstruction loss to overcome these dataset issues. In particular, we extract commonsense knowledge from the external knowledge base to refine object and phrase features for improving generalizability in scene graph generation. To address the bias of noisy object annotations, we introduce an auxiliary image reconstruction path to regularize the scene graph generation network. Extensive experiments show that our framework can generate better scene graphs, achieving the state-of-the-art performance on two benchmark datasets: Visual Relationship Detection and Visual Genome datasets.

10 pages, 5 figures, Accepted in CVPR 2019

References in corpus (3)

• Distilling the Knowledge in a Neural Network
• Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks
• Natural Language Guided Visual Relationship Detection

Cited by in corpus (4)

• Dual ResGCN for Balanced Scene GraphGeneration
• Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation
• Recovering the Unbiased Scene Graphs from the Biased Ones
• MeronymNet: A Hierarchical Approach for Unified and Controllable Multi-Category Object Generation