mlsanityData to 14 Oct 2026

Predicate correlation learning for scene graph generation

arXiv 2107.02713 ↗First posted 6 Jul 2021cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

For a typical Scene Graph Generation (SGG) method, there is often a large gap in the performance of the predicates' head classes and tail classes. This phenomenon is mainly caused by the semantic overlap between different predicates as well as the long-tailed data distribution. In this paper, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the above two problems by taking the correlation between predicates into consideration. To describe the semantic overlap between strong-correlated predicate classes, a Predicate Correlation Matrix (PCM) is defined to quantify the relationship between predicate pairs, which is dynamically updated to remove the matrix's long-tailed bias. In addition, PCM is integrated into a Predicate Correlation Loss function (LPC) to reduce discouraging gradients of unannotated classes. The proposed method is evaluated on Visual Genome benchmark, where the performance of the tail classes is significantly improved when built on the existing methods.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 33 of its 48 references that are in the map. First posted on arXiv 6 Jul 2021.

Builds on

33 of 48 references.

References · 33

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  6. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  7. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  8. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  9. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  10. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 414
  11. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 356
  12. 2016Visual Relationship Detection with Language Priorscited by 334
21 more
  1. 2018Graph R-CNN for Scene Graph Generationcited by 298
  2. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  3. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 259
  4. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 255
  5. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  6. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 166
  7. 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 164
  8. 2017Scene Graph Generation from Objects, Phrases and Region Captionscited by 154
  9. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  10. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
  11. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  12. 2017Detecting Visual Relationships with Deep Relational Networkscited by 97
  13. 2019Unpaired Image Captioning via Scene Graph Alignmentscited by 82
  14. 2019Striking the Right Balance with Uncertaintycited by 79
  15. 2018Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generationcited by 78
  16. 2020PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generationcited by 75
  17. 2020CogTree: Cognition Tree Loss for Unbiased Scene Graph Generationcited by 62
  18. 2017Visual Relationship Detection with Internal and External Linguistic Knowledge Distillationcited by 61
  19. 2019Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attentioncited by 26
  20. 2018Clustering and Learning from Imbalanced Datacited by 7
  21. 2019Scene Graph based Image Retrieval -- A case study on the CLEVR Datasetcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 1; 2025: 3.

11 papers.

  1. 2022Hierarchical Memory Learning for Fine-Grained Scene Graph Generationcited by 15
  2. 2022Adaptive Fine-Grained Predicates Learning for Scene Graph Generationcited by 14
  3. 2025A Causal Adjustment Module for Debiasing Scene Graph Generationcited by 14
  4. 2022Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generationcited by 10
  5. 2023Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generationcited by 10
  6. 2024Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentationcited by 7
  7. 2025Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generationcited by 7
  8. 2023Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generationcited by 3
  9. 2023Generalized Unbiased Scene Graph Generationcited by 3
  10. 2025A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generationcited by 1
  11. 2023Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generationcited by 0