mlsanityData to 14 Oct 2026

Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation

arXiv 2201.06794 ↗First posted 18 Jan 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Scene Graph Generation (SGG) aims to build a structured representation of a scene using objects and pairwise relationships, which benefits downstream tasks. However, current SGG methods usually suffer from sub-optimal scene graph generation because of the long-tailed distribution of training data. To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation. Specifically, RTPB uses a distributed-based prior bias to improve models' detecting ability on less frequent relationships during training, thus improving the model generalizability on tail categories. In addition, to further explore the contextual information of objects and relationships, we design a contextual encoding backbone network, termed as Dual Transformer (DTrans). We perform extensive experiments on a very popular benchmark, VG150, to demonstrate the effectiveness of our method for the unbiased scene graph generation. In specific, our RTPB achieves an improvement of over 10% under the mean recall when applied to current SGG methods. Furthermore, DTrans with RTPB outperforms nearly all state-of-the-art methods with a large margin.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 18 Jan 2022.

Builds on

24 of 35 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  6. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  7. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  8. 2020Long-tail learning via logit adjustmentcited by 618
  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
12 more
  1. 2018Graph R-CNN for Scene Graph Generationcited by 298
  2. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 259
  3. 2020GPS-Net: Graph Property Sensing Network for Scene Graph Generationcited by 166
  4. 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 164
  5. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  6. 2018Gradient Harmonized Single-stage Detectorcited by 114
  7. 2019Scene Graph Generation with External Knowledge and Image Reconstructioncited by 102
  8. 2020PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generationcited by 75
  9. 2021Recovering the Unbiased Scene Graphs from the Biased Onescited by 71
  10. 2017Visual Relationship Detection with Internal and External Linguistic Knowledge Distillationcited by 61
  11. 2020Comprehensive Image Captioning via Scene Graph Decompositioncited by 52
  12. 2019On Exploring Undetermined Relationships for Visual Relationship Detectioncited by 26

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 7; 2024: 4; 2025: 4; 2026: 1.

22 papers.

Sort:

By area:

  1. 2024STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagerycited by 31
  2. 2023Unbiased Scene Graph Generation via Two-stage Causal Modelingcited by 21
  3. 2022Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Networkcited by 17
  4. 2023Compositional Feature Augmentation for Unbiased Scene Graph Generationcited by 15
  5. 2022Adaptive Fine-Grained Predicates Learning for Scene Graph Generationcited by 14
  6. 2024HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generationcited by 14
  7. 2025A Causal Adjustment Module for Debiasing Scene Graph Generationcited by 14
  8. 2022Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generationcited by 10
  9. 2022Rethinking the Evaluation of Unbiased Scene Graph Generationcited by 9
  10. 20253D Human Interaction Generation: A Surveycited by 7
  11. 2024AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generationcited by 5
  12. 2022Peer Learning for Unbiased Scene Graph Generationcited by 4
10 more
  1. 2022Context-aware Mixture-of-Experts for Unbiased Scene Graph Generationcited by 3
  2. 2023Generalized Unbiased Scene Graph Generationcited by 3
  3. 2023LANDMARK: Language-guided Representation Enhancement Framework for Scene Graph Generationcited by 2
  4. 2023RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generationcited by 2
  5. 2023Zero-Shot Scene Graph Generation via Triplet Calibration and Reductioncited by 2
  6. 2024Fine-Grained Scene Graph Generation via Sample-Level Bias Predictioncited by 1
  7. 2025UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generationcited by 1
  8. 2025A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generationcited by 1
  9. 2026Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimationcited by 1
  10. 2023Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generationcited by 0