mlsanityData to 14 Oct 2026

Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation

arXiv 2601.08728 ↗First posted 13 Jan 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address this issue by implementing debiasing strategies, but often at the cost of spatial understanding, resulting in an over-reliance on semantic priors. We introduce Salience-SGG, a novel framework featuring an Iterative Salience Decoder (ISD) that emphasizes triplets with salient spatial structures. To support this, we propose semantic-agnostic salience labels guiding ISD. Evaluations on Visual Genome, Open Images V6, and GQA-200 show that Salience-SGG achieves state-of-the-art performance and improves existing Unbiased-SGG methods in their spatial understanding as demonstrated by the Pairwise Localization Average Precision

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 13 Jan 2026.

Builds on

45 of 58 references.

References · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  6. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  7. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 544
  8. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  9. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 414
  10. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 356
  11. 2016Visual Relationship Detection with Language Priorscited by 334
  12. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 259
33 more
  1. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 166
  2. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  3. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  4. 2017Visual Translation Embedding Network for Visual Relation Detectioncited by 112
  5. 2021SGTR: End-to-end Scene Graph Generation with Transformercited by 103
  6. 2017Detecting Visual Relationships with Deep Relational Networkscited by 97
  7. 2022RelTR: Relation Transformer for Scene Graph Generationcited by 96
  8. 2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
  9. 2021Learning of Visual Relations: The Devil is in the Tailscited by 65
  10. 2022The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generationcited by 60
  11. 2022Fine-Grained Scene Graph Generation with Data Transfercited by 57
  12. 2024EGTR: Extracting Graph from Transformer for Scene Graph Generationcited by 47
  13. 2018LinkNet: Relational Embedding for Scene Graphcited by 45
  14. 2021Structured Sparse R-CNN for Direct Scene Graph Generationcited by 44
  15. 2018Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognitioncited by 41
  16. 2023Less is More: Focus Attention for Efficient DETRcited by 38
  17. 2023Prototype-based Embedding Network for Scene Graph Generationcited by 37
  18. 2021Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queriescited by 31
  19. 2024Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinementcited by 31
  20. 2022RU-Net: Regularized Unrolling Network for Scene Graph Generationcited by 28
  21. 2024Relation DETR: Exploring Explicit Position Relation Prior for Object Detectioncited by 28
  22. 2022Iterative Scene Graph Generationcited by 24
  23. 2023Devil's on the Edges: Selective Quad Attention for Scene Graph Generationcited by 23
  24. 2022Resistance Training using Prior Bias: toward Unbiased Scene Graph Generationcited by 22
  25. 2021Not All Relations are Equal: Mining Informative Labels for Scene Graph Generationcited by 21
  26. 2023Vision Relation Transformer for Unbiased Scene Graph Generationcited by 18
  27. 2023Pair then Relation: Pair-Net for Panoptic Scene Graph Generationcited by 17
  28. 2024Adaptive Self-training Framework for Fine-grained Scene Graph Generationcited by 11
  29. 2024Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detectioncited by 11
  30. 2024Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generationcited by 10
  31. 2023Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generationcited by 9
  32. 2024Leveraging Predicate and Triplet Learning for Scene Graph Generationcited by 8
  33. 2024RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachabilitycited by 0