# EGTR: Extracting Graph from Transformer for Scene Graph Generation

arXiv: https://arxiv.org/abs/2404.02072 · HTML: https://mlsanity.com/paper/2404.02072/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Scene Graph Generation by Iterative Message Passing](https://mlsanity.com/paper/1701.02426/) (2017)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Visual Relationship Detection with Language Priors](https://mlsanity.com/paper/1608.00187/) (2016)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [Graph R-CNN for Scene Graph Generation](https://mlsanity.com/paper/1808.00191/) (2018)
- [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018)
- [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018)
- [GPS-Net: Graph Property Sensing Network for Scene Graph Generation](https://mlsanity.com/paper/2003.12962/) (2020)
- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [Relation-Aware Graph Attention Network for Visual Question Answering](https://mlsanity.com/paper/1903.12314/) (2019)
- [Visual Translation Embedding Network for Visual Relation Detection](https://mlsanity.com/paper/1702.08319/) (2017)
- [Energy-Based Learning for Scene Graph Generation](https://mlsanity.com/paper/2103.02221/) (2021)
- [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021)
- [Graphical Contrastive Losses for Scene Graph Parsing](https://mlsanity.com/paper/1903.02728/) (2019)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [Relationformer: A Unified Framework for Image-to-Graph Generation](https://mlsanity.com/paper/2203.10202/) (2022)
- [Pixels to Graphs by Associative Embedding](https://mlsanity.com/paper/1706.07365/) (2017)
- [Fully Convolutional Scene Graph Generation](https://mlsanity.com/paper/2103.16083/) (2021)

## Built on by (most cited first, 30 of 47)

- [HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation](https://mlsanity.com/paper/2411.18042/) (2024)
- [CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos](https://mlsanity.com/paper/2406.01029/) (2024)
- [Universal Scene Graph Generation](https://mlsanity.com/paper/2503.15005/) (2025)
- [FROSS: Faster-than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images](https://mlsanity.com/paper/2507.19993/) (2025)
- [Reusing Attention for One-stage Lane Topology Understanding](https://mlsanity.com/paper/2507.17617/) (2025)
- [Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene](https://mlsanity.com/paper/2503.15019/) (2025)
- [AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks](https://mlsanity.com/paper/2411.16749/) (2024)
- [DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes](https://mlsanity.com/paper/2505.03581/) (2025)
- [VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models](https://mlsanity.com/paper/2511.07299/) (2025)
- [REACT: Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation](https://mlsanity.com/paper/2405.16116/) (2024)
- [BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation](https://mlsanity.com/paper/2407.18715/) (2024)
- [Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation](https://mlsanity.com/paper/2504.12606/) (2025)
- [SATURN: Autoregressive Image Generation Guided by Scene Graphs](https://mlsanity.com/paper/2508.14502/) (2025)
- [GraSP-VLA: Graph-based Symbolic Action Representation for Long-Horizon Planning with VLA Policies](https://mlsanity.com/paper/2511.04357/) (2025)
- [A Modern Take on Visual Relationship Reasoning for Grasp Planning](https://mlsanity.com/paper/2409.02035/) (2024)
- [DroneKey: Drone 3D Pose Estimation in Image Sequences using Gated Key-representation and Pose-adaptive Learning](https://mlsanity.com/paper/2508.17746/) (2025)
- [PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction](https://mlsanity.com/paper/2512.10888/) (2025)
- [FORESCENE: FOREcasting human activity via latent SCENE graphs diffusion](https://mlsanity.com/paper/2503.06182/) (2025)
- [SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation](https://mlsanity.com/paper/2503.18988/) (2025)
- [Assured Autonomy with Neuro-Symbolic Perception](https://mlsanity.com/paper/2505.21322/) (2025)
- [A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2505.23451/) (2025)
- [FDSG: Forecasting Dynamic Scene Graphs](https://mlsanity.com/paper/2506.01487/) (2025)
- [Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation](https://mlsanity.com/paper/2601.08728/) (2026)
- [REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generation](https://mlsanity.com/paper/2603.06386/) (2026)
- [HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning](https://mlsanity.com/paper/2606.06100/) (2026)
- [DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors](https://mlsanity.com/paper/2607.00889/) (2026)
- [Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs](https://mlsanity.com/paper/2607.02425/) (2026)
- [A document is worth a structured record: Principled inductive bias design for document recognition](https://mlsanity.com/paper/2507.08458/) (2025)
- [THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footage](https://mlsanity.com/paper/2507.09200/) (2025)
- [SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding](https://mlsanity.com/paper/2512.00936/) (2025)

## Abstract (arXiv)

Scene Graph Generation (SGG) is a challenging task of detecting objects and predicting relationships between objects. After DETR was developed, one-stage SGG models based on a one-stage object detector have been actively studied. However, complex modeling is used to predict the relationship between objects, and the inherent relationship between object queries learned in the multi-head self-attention of the object detector has been neglected. We propose a lightweight one-stage SGG model that extracts the relation graph from the various relationships learned in the multi-head self-attention layers of the DETR decoder. By fully utilizing the self-attention by-products, the relation graph can be extracted effectively with a shallow relation extraction head. Considering the dependency of the relation extraction task on the object detection task, we propose a novel relation smoothing technique that adjusts the relation label adaptively according to the quality of the detected objects. By the relation smoothing, the model is trained according to the continuous curriculum that focuses on object detection task at the beginning of training and performs multi-task learning as the object detection performance gradually improves. Furthermore, we propose a connectivity prediction task that predicts whether a relation exists between object pairs as an auxiliary task of the relation extraction. We demonstrate the effectiveness and efficiency of our method for the Visual Genome and Open Image V6 datasets. Our code is publicly available at https://github.com/naver-ai/egtr.