RelTR: Relation Transformer for Scene Graph Generation

Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 45; H. 9; S. 11169 - 11183
Hauptverfasser: Cong, Yuren, Yang, Michael Ying, Rosenhahn, Bodo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.09.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Coders
Decoding
Encoders-Decoders
Object detection
Object recognition
One-stage
Predictions
Predictive models
Proposals
scene graph generation
scene understanding
Task analysis
Transformers
visual relationship detection
Visualization
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an end-to-end scene graph generation model Relation Transformer (RelTR), which has an encoder-decoder architecture. The encoder reasons about the visual feature context while the decoder infers a fixed-size set of triplets subject-predicate-object using different types of attention mechanisms with coupled subject and object queries. We design a set prediction loss performing the matching between the ground truth and predicted triplets for the end-to-end training. In contrast to most existing scene graph generation methods, RelTR is a one-stage method that predicts sparse scene graphs directly only using visual appearance without combining entities and labeling all possible predicates. Extensive experiments on the Visual Genome, Open Images V6, and VRD datasets demonstrate the superior performance and fast inference of our model.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2023.3268066