REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation
Not on the map. Why?
Abstract (arXiv)
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
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 49 references that are in the map. First posted on arXiv 25 May 2024.
Builds on
30 of 49 references.
References · 30
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
- 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
- 2017Scene Graph Generation by Iterative Message Passingcited by 462
- 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
- 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 414
- 2020Unbiased Scene Graph Generation from Biased Trainingcited by 356
- 2016Visual Relationship Detection with Language Priorscited by 334
- 2018Graph R-CNN for Scene Graph Generationcited by 298
- 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 259
18 more
- 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 166
- 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
- 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
- 2022Panoptic Scene Graph Generationcited by 114
- 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 103
- 2022RelTR: Relation Transformer for Scene Graph Generationcited by 96
- 2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
- 2024EGTR: Extracting Graph from Transformer for Scene Graph Generationcited by 47
- 2021Structured Sparse R-CNN for Direct Scene Graph Generationcited by 44
- 2022Continuous Scene Representations for Embodied AIcited by 39
- 2023Prototype-based Embedding Network for Scene Graph Generationcited by 37
- 2018Large-Scale Visual Relationship Understandingcited by 33
- 2021In Defense of Scene Graphs for Image Captioningcited by 31
- 2021ReFormer: The Relational Transformer for Image Captioningcited by 23
- 2023Devil's on the Edges: Selective Quad Attention for Scene Graph Generationcited by 23
- 2021Understanding the Role of Scene Graphs in Visual Question Answeringcited by 20
- 2021GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answeringcited by 16
- 2023Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generationcited by 4
Built on by
Citing papers per year: 2026: 3.
3 papers.