# Probabilistic Debiasing of Scene Graphs arXiv: https://arxiv.org/abs/2211.06444 ยท HTML: https://mlsanity.com/paper/2211.06444/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Builds on 36 of its 50 references that are in the map. - First posted on arXiv 11 Nov 2022. ## Builds on (most cited first, 30 of 36) - [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016) - [Scene Graph Generation by Iterative Message Passing](https://mlsanity.com/paper/1701.02426/) (2017) - [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017) - [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020) - [Visual Relationship Detection with Language Priors](https://mlsanity.com/paper/1608.00187/) (2016) - [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018) - [Graph R-CNN for Scene Graph Generation](https://mlsanity.com/paper/1808.00191/) (2018) - [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018) - [Auto-Encoding Scene Graphs for Image Captioning](https://mlsanity.com/paper/1812.02378/) (2018) - [GPS-Net: Graph Property Sensing Network for Scene Graph Generation](https://mlsanity.com/paper/2003.12962/) (2020) - [Knowledge-Embedded Routing Network for Scene Graph Generation](https://mlsanity.com/paper/1903.03326/) (2019) - [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021) - [Visual Translation Embedding Network for Visual Relation Detection](https://mlsanity.com/paper/1702.08319/) (2017) - [Energy-Based Learning for Scene Graph Generation](https://mlsanity.com/paper/2103.02221/) (2021) - [Explainable and Explicit Visual Reasoning over Scene Graphs](https://mlsanity.com/paper/1812.01855/) (2018) - [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021) - [Scene Graph Generation with External Knowledge and Image Reconstruction](https://mlsanity.com/paper/1904.00560/) (2019) - [Graphical Contrastive Losses for Scene Graph Parsing](https://mlsanity.com/paper/1903.02728/) (2019) - [Detecting Visual Relationships with Deep Relational Networks](https://mlsanity.com/paper/1704.03114/) (2017) - [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022) - [Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias](https://mlsanity.com/paper/2001.03152/) (2020) - [Bridging Knowledge Graphs to Generate Scene Graphs](https://mlsanity.com/paper/2001.02314/) (2020) - [Recovering the Unbiased Scene Graphs from the Biased Ones](https://mlsanity.com/paper/2107.02112/) (2021) - [Learning of Visual Relations: The Devil is in the Tails](https://mlsanity.com/paper/2108.09668/) (2021) - [Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation](https://mlsanity.com/paper/1707.09423/) (2017) - [The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation](https://mlsanity.com/paper/2206.03014/) (2022) - [From General to Specific: Informative Scene Graph Generation via Balance Adjustment](https://mlsanity.com/paper/2108.13129/) (2021) - [Learning Visual Commonsense for Robust Scene Graph Generation](https://mlsanity.com/paper/2006.09623/) (2020) - [LinkNet: Relational Embedding for Scene Graph](https://mlsanity.com/paper/1811.06410/) (2018) - [Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation](https://mlsanity.com/paper/2103.05271/) (2021) ## Built on by (most cited first, 8 of 8) - [HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding](https://mlsanity.com/paper/2312.03050/) (2023) - [A Causal Adjustment Module for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2503.17862/) (2025) - [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024) - [Improving Scene Graph Generation with Superpixel-Based Interaction Learning](https://mlsanity.com/paper/2308.02339/) (2023) - [Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Models](https://mlsanity.com/paper/2401.01130/) (2024) - [Generalized Unbiased Scene Graph Generation](https://mlsanity.com/paper/2308.04802/) (2023) - [Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction](https://mlsanity.com/paper/2407.19259/) (2024) - [Enhanced Data Transfer Cooperating with Artificial Triplets for Scene Graph Generation](https://mlsanity.com/paper/2406.19316/) (2024) ## Abstract (arXiv) The quality of scene graphs generated by the state-of-the-art (SOTA) models is compromised due to the long-tail nature of the relationships and their parent object pairs. Training of the scene graphs is dominated by the majority relationships of the majority pairs and, therefore, the object-conditional distributions of relationship in the minority pairs are not preserved after the training is converged. Consequently, the biased model performs well on more frequent relationships in the marginal distribution of relationships such as `on' and `wearing', and performs poorly on the less frequent relationships such as `eating' or `hanging from'. In this work, we propose virtual evidence incorporated within-triplet Bayesian Network (BN) to preserve the object-conditional distribution of the relationship label and to eradicate the bias created by the marginal probability of the relationships. The insufficient number of relationships in the minority classes poses a significant problem in learning the within-triplet Bayesian network. We address this insufficiency by embedding-based augmentation of triplets where we borrow samples of the minority triplet classes from its neighborhood triplets in the semantic space. We perform experiments on two different datasets and achieve a significant improvement in the mean recall of the relationships. We also achieve better balance between recall and mean recall performance compared to the SOTA de-biasing techniques of scene graph models.