DDS: Decoupled Dynamic Scene-Graph Generation Network

01/18/2023
by   A. S. M. Iftekhar, et al.
5

Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data. However, existing methods show poor performance in detecting triplets outside of a predefined set, primarily due to their reliance on dependent feature learning. To address this issue we propose DDS – a decoupled dynamic scene-graph generation network – that consists of two independent branches that can disentangle extracted features. The key innovation of the current paper is the decoupling of the features representing the relationships from those of the objects, which enables the detection of novel object-relationship combinations. The DDS model is evaluated on three datasets and outperforms previous methods by a significant margin, especially in detecting previously unseen triplets.

READ FULL TEXT

page 1

page 3

page 8

page 9

research
01/27/2022

RelTR: Relation Transformer for Scene Graph Generation

Different objects in the same scene are more or less related to each oth...
research
01/18/2022

Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation

Scene Graph Generation (SGG) aims to build a structured representation o...
research
02/15/2022

Hyper-relationship Learning Network for Scene Graph Generation

Generating informative scene graphs from images requires integrating and...
research
03/08/2019

Knowledge-Embedded Routing Network for Scene Graph Generation

To understand a scene in depth not only involves locating/recognizing in...
research
09/21/2023

SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphs

Object rearrangement is pivotal in robotic-environment interactions, rep...
research
03/07/2019

Graphical Contrastive Losses for Scene Graph Generation

Most scene graph generators use a two-stage pipeline to detect visual re...
research
10/12/2021

Topic Scene Graph Generation by Attention Distillation from Caption

If an image tells a story, the image caption is the briefest narrator. G...

Please sign up or login with your details

Forgot password? Click here to reset