Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation - Ecole Nationale d'Ingénieurs de Brest Access content directly
Conference Papers Year : 2023

Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation

Abstract

Learning to compose visual relationships from raw images in the form of scene graphs is a highly challenging task due to contextual dependencies, but it is essential in computer vision applications that depend on scene understanding. However, no current approaches in Scene Graph Generation (SGG) aim at providing useful graphs for downstream tasks. Instead, the main focus has primarily been on the task of unbiasing the data distribution for predicting more fine-grained relations. That being said, all fine-grained relations are not equally relevant and at least a part of them are of no use for real-world applications. In this work, we introduce the task of Efficient SGG that prioritizes the generation of relevant relations, facilitating the use of Scene Graphs in downstream tasks such as Image Generation. To support further approaches, we present a new dataset, VG150-curated, based on the annotations of the popular Visual Genome dataset. We show through a set of experiments that this dataset contains more high-quality and diverse annotations than the one usually use in SGG. Finally, we show the efficiency of this dataset in the task of Image Generation from Scene Graphs.
Fichier principal
Vignette du fichier
Neau_Fine-Grained_is_Too_Coarse_A_Novel_Data-Centric_Approach_for_Efficient_ICCVW_2023_paper.pdf (1.59 Mo) Télécharger le fichier
Origin Publisher files allowed on an open archive
licence
Copyright

Dates and versions

hal-04585080 , version 1 (23-05-2024)

Licence

Copyright

Identifiers

Cite

Neau Maëlic, Paulo E. Santos, Anne-Gwenn Bosser, Cédric Buche. Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation. IEEE/CVF International Conference on Computer Vision (ICCV) 2023, Oct 2023, Paris, France. pp.11-20. ⟨hal-04585080⟩
0 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More