mlsanityData to 7 Oct 2026

Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability

arXiv 2607.06176 ↗First posted 7 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Scene graph generation (SGG) approaches can be broadly classified into detector-based and query-based methods according to their underlying reasoning mechanisms. However, the discrepancy in their predictive behaviors, induced by these distinct mechanisms, has not been systematically analyzed. In this work, we design a controlled experimental setup to examine prediction discrepancies from the perspective of detector-conditioned reachability. The results suggest clear complementary clues. Motivated by this observation, we introduce a Dual-SGG method that consolidates both reasoning mechanisms via a dual-query design, thereby leveraging the complementary predictive behaviors of both detector-based and query-based methods. Extensive experiments on the Visual Genome, Open Images v6, and GQA-200 datasets demonstrate the effectiveness of the proposed method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 52 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

43 of 52 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  8. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  9. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  10. 2020Long-tail learning via logit adjustmentcited by 605
  11. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  12. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
31 more
  1. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  2. 2016Visual Relationship Detection with Language Priorscited by 333
  3. 2018Image Generation from Scene Graphscited by 324
  4. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
  5. 2022DETRs with Hybrid Matchingcited by 149
  6. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  7. 2017Visual Translation Embedding Network for Visual Relation Detectioncited by 112
  8. 2018Explainable and Explicit Visual Reasoning over Scene Graphscited by 103
  9. 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 102
  10. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
  11. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 95
  12. 2021Multimodal Object Detection via Probabilistic Ensemblingcited by 67
  13. 2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
  14. 2022Relationformer: A Unified Framework for Image-to-Graph Generationcited by 67
  15. 2021Learning of Visual Relations: The Devil is in the Tailscited by 65
  16. 2022Fine-Grained Scene Graph Generation with Data Transfercited by 57
  17. 2024EGTR: Extracting Graph from Transformer for Scene Graph Generationcited by 45
  18. 2019PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graphcited by 44
  19. 2021Structured Sparse R-CNN for Direct Scene Graph Generationcited by 44
  20. 2023Prototype-based Embedding Network for Scene Graph Generationcited by 37
  21. 2024MS-DETR: Efficient DETR Training with Mixed Supervisioncited by 34
  22. 2021In Defense of Scene Graphs for Image Captioningcited by 31
  23. 2022RU-Net: Regularized Unrolling Network for Scene Graph Generationcited by 28
  24. 2022Iterative Scene Graph Generationcited by 24
  25. 2023Devil's on the Edges: Selective Quad Attention for Scene Graph Generationcited by 23
  26. 2023Vision Relation Transformer for Unbiased Scene Graph Generationcited by 18
  27. 2024Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detectioncited by 11
  28. 2024Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generationcited by 10
  29. 2024Leveraging Predicate and Triplet Learning for Scene Graph Generationcited by 8
  30. 2024RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learningcited by 6
  31. 2026Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimationcited by 1

Built on by

Not cited yet.