mlsanityData to 7 Oct 2026

Fine-Grained Scene Graph Generation with Data Transfer

arXiv 2203.11654 ↗First posted 22 Mar 2022cs.CV cs.AIcited by 57

Not on the map. Why?

Abstract (arXiv)

Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images. Recent works have made a steady progress on SGG, and provide useful tools for high-level vision and language understanding. However, due to the data distribution problems including long-tail distribution and semantic ambiguity, the predictions of current SGG models tend to collapse to several frequent but uninformative predicates (e.g., on, at), which limits practical application of these models in downstream tasks. To deal with the problems above, we propose a novel Internal and External Data Transfer (IETrans) method, which can be applied in a plug-and-play fashion and expanded to large SGG with 1,807 predicate classes. Our IETrans tries to relieve the data distribution problem by automatically creating an enhanced dataset that provides more sufficient and coherent annotations for all predicates. By training on the enhanced dataset, a Neural Motif model doubles the macro performance while maintaining competitive micro performance. The code and data are publicly available at https://github.com/waxnkw/IETrans-SGG.pytorch.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 22 Mar 2022.

Builds on

34 of 42 references.

References · 34

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  5. 2015VQA: Visual Question Answeringcited by 2,489
  6. 2017Focal Loss for Dense Object Detectioncited by 749
  7. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  8. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  9. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  10. 2016Visual Relationship Detection with Language Priorscited by 333
  11. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
  12. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 254
22 more
  1. 2021CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Modelscited by 182
  2. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 165
  3. 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 163
  4. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  5. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  6. 2016Graph-Structured Representations for Visual Question Answeringcited by 123
  7. 2021Energy-Based Learning for Scene Graph Generationcited by 104
  8. 2020Bridging Knowledge Graphs to Generate Scene Graphscited by 86
  9. 2019Unpaired Image Captioning via Scene Graph Alignmentscited by 82
  10. 2020PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generationcited by 75
  11. 2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
  12. 2021Video as Conditional Graph Hierarchy for Multi-Granular Question Answeringcited by 68
  13. 2019Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrievalcited by 66
  14. 2021Learning of Visual Relations: The Devil is in the Tailscited by 65
  15. 2020CogTree: Cognition Tree Loss for Unbiased Scene Graph Generationcited by 62
  16. 2021From General to Specific: Informative Scene Graph Generation via Balance Adjustmentcited by 51
  17. 2020NBDT: Neural-Backed Decision Treescited by 46
  18. 2018Large-Scale Visual Relationship Understandingcited by 33
  19. 2021Visual Distant Supervision for Scene Graph Generationcited by 25
  20. 2020Exploring Long Tail Visual Relationship Recognition with Large Vocabularycited by 16
  21. 2021Rethinking the Two-Stage Framework for Grounded Situation Recognitioncited by 16
  22. 2021Semantic Compositional Learning for Low-shot Scene Graph Generationcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 30; 2024: 14; 2025: 7; 2026: 3.

57 papers.

Sort:

By area:

  1. 2023Exploring Diverse In-Context Configurations for Image Captioningcited by 63
  2. 2024From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Modelscited by 43
  3. 2023Panoptic Scene Graph Generation with Semantics-Prototype Learningcited by 42
  4. 2023Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open Worldcited by 35
  5. 2023How to Configure Good In-Context Sequence for Visual Question Answeringcited by 31
  6. 2022PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Modelscited by 30
  7. 2023LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generationcited by 30
  8. 2023Devil's on the Edges: Selective Quad Attention for Scene Graph Generationcited by 23
  9. 2023Unbiased Scene Graph Generation via Two-stage Causal Modelingcited by 21
  10. 2023HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generationcited by 19
  11. 2023Vision Relation Transformer for Unbiased Scene Graph Generationcited by 18
  12. 2023Compositional Feature Augmentation for Unbiased Scene Graph Generationcited by 15
38 more
  1. 2022Adaptive Fine-Grained Predicates Learning for Scene Graph Generationcited by 14
  2. 2025A Causal Adjustment Module for Debiasing Scene Graph Generationcited by 14
  3. 2023Unified Visual Relationship Detection with Vision and Language Modelscited by 13
  4. 2023VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generationcited by 12
  5. 2024Adaptive Self-training Framework for Fine-grained Scene Graph Generationcited by 11
  6. 2023Towards Complex-query Referring Image Segmentation: A Novel Benchmarkcited by 10
  7. 2024Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generationcited by 10
  8. 2023Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generationcited by 9
  9. 2023Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classescited by 8
  10. 2024Leveraging Predicate and Triplet Learning for Scene Graph Generationcited by 8
  11. 2023Domain-wise Invariant Learning for Panoptic Scene Graph Generationcited by 7
  12. 2023Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledgecited by 7
  13. 2024Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detectioncited by 6
  14. 2024RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learningcited by 6
  15. 2023Skew Class-balanced Re-weighting for Unbiased Scene Graph Generationcited by 5
  16. 2024AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generationcited by 5
  17. 2023Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generationcited by 4
  18. 2023In Defense of Clip-based Video Relation Detectioncited by 4
  19. 2023Improving Scene Graph Generation with Superpixel-Based Interaction Learningcited by 4
  20. 2024A Fair Ranking and New Model for Panoptic Scene Graph Generationcited by 4
  21. 2024Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generationcited by 4
  22. 2023Generalized Unbiased Scene Graph Generationcited by 3
  23. 2023STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoningcited by 3
  24. 2024From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generationcited by 3
  25. 2024BCTR: Bidirectional Conditioning Transformer for Scene Graph Generationcited by 3
  26. 2023Informative Scene Graph Generation via Debiasingcited by 2
  27. 2023RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generationcited by 2
  28. 2023Open-Set Knowledge-Based Visual Question Answering with Inference Pathscited by 2
  29. 2024A Review and Efficient Implementation of Scene Graph Generation Metricscited by 2
  30. 2022Visually Grounded Commonsense Knowledge Acquisitioncited by 1
  31. 2023Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstructioncited by 1
  32. 2024Fine-Grained Scene Graph Generation via Sample-Level Bias Predictioncited by 1
  33. 2025UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generationcited by 1
  34. 2025A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generationcited by 1
  35. 2025Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generationcited by 1
  36. 2026Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimationcited by 1
  37. 2023Logical Bias Learning for Object Relation Predictioncited by 0
  38. 2023VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Toolscited by 0

50 most cited of 57 All 57 (JSON)