REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Neau, Maëlic, Santos, Paulo E., Bosser, Anne-Gwenn, Buche, Cédric, Sugimoto, Akihiro
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911169893105664
author Neau, Maëlic
Santos, Paulo E.
Bosser, Anne-Gwenn
Buche, Cédric
Sugimoto, Akihiro
author_facet Neau, Maëlic
Santos, Paulo E.
Bosser, Anne-Gwenn
Buche, Cédric
Sugimoto, Akihiro
contents Scene Graph Generation (SGG) is a task that encodes visual relationships between objects in images as graph structures. SGG shows significant promise as a foundational component for downstream tasks, such as reasoning for embodied agents. To enable real-time applications, SGG must address the trade-off between performance and inference speed. However, current methods tend to focus on one of the following: (1) improving relation prediction accuracy, (2) enhancing object detection accuracy, or (3) reducing latency, without aiming to balance all three objectives simultaneously. To address this limitation, we propose the Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation (REACT) architecture, which achieves the highest inference speed among existing SGG models, improving object detection accuracy without sacrificing relation prediction performance. Compared to state-of-the-art approaches, REACT is 2.7 times faster and improves object detection accuracy by 58\%. Furthermore, our proposal significantly reduces model size, with an average of 5.5x fewer parameters. The code is available at https://github.com/Maelic/SGG-Benchmark
format Preprint
id arxiv_https___arxiv_org_abs_2405_16116
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
Neau, Maëlic
Santos, Paulo E.
Bosser, Anne-Gwenn
Buche, Cédric
Sugimoto, Akihiro
Computer Vision and Pattern Recognition
Scene Graph Generation (SGG) is a task that encodes visual relationships between objects in images as graph structures. SGG shows significant promise as a foundational component for downstream tasks, such as reasoning for embodied agents. To enable real-time applications, SGG must address the trade-off between performance and inference speed. However, current methods tend to focus on one of the following: (1) improving relation prediction accuracy, (2) enhancing object detection accuracy, or (3) reducing latency, without aiming to balance all three objectives simultaneously. To address this limitation, we propose the Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation (REACT) architecture, which achieves the highest inference speed among existing SGG models, improving object detection accuracy without sacrificing relation prediction performance. Compared to state-of-the-art approaches, REACT is 2.7 times faster and improves object detection accuracy by 58\%. Furthermore, our proposal significantly reduces model size, with an average of 5.5x fewer parameters. The code is available at https://github.com/Maelic/SGG-Benchmark
title REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.16116