# Compositional Feature Augmentation for Unbiased Scene Graph Generation arXiv: https://arxiv.org/abs/2308.06712 ยท HTML: https://mlsanity.com/paper/2308.06712/ ## Key facts - Cited by 15 papers in the map (data through 14 Oct 2026). - Builds on 45 of its 51 references that are in the map. - First posted on arXiv 13 Aug 2023. ## Builds on (most cited first, 30 of 45) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020) - [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015) - [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017) - [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016) - [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016) - [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017) - [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017) - [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019) - [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019) - [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) - [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018) - [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) - [Feature Space Augmentation for Long-Tailed Data](https://mlsanity.com/paper/2008.03673/) (2020) - [Visual Compositional Learning for Human-Object Interaction Detection](https://mlsanity.com/paper/2007.12407/) (2020) - [Visual Translation Embedding Network for Visual Relation Detection](https://mlsanity.com/paper/1702.08319/) (2017) - [Detecting Human-Object Interaction via Fabricated Compositional Learning](https://mlsanity.com/paper/2103.08214/) (2021) - [PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2009.00893/) (2020) - [Recovering the Unbiased Scene Graphs from the Biased Ones](https://mlsanity.com/paper/2107.02112/) (2021) - [Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2203.09811/) (2022) - [Learning of Visual Relations: The Devil is in the Tails](https://mlsanity.com/paper/2108.09668/) (2021) - [CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2009.07526/) (2020) - [The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation](https://mlsanity.com/paper/2206.03014/) (2022) - [Fine-Grained Scene Graph Generation with Data Transfer](https://mlsanity.com/paper/2203.11654/) (2022) - [Counterfactual Critic Multi-Agent Training for Scene Graph Generation](https://mlsanity.com/paper/1812.02347/) (2018) - [From General to Specific: Informative Scene Graph Generation via Balance Adjustment](https://mlsanity.com/paper/2108.13129/) (2021) ## Built on by (most cited first, 15 of 15) - [EGTR: Extracting Graph from Transformer for Scene Graph Generation](https://mlsanity.com/paper/2404.02072/) (2024) - [LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation](https://mlsanity.com/paper/2310.10404/) (2023) - [Scene Graph Generation with Role-Playing Large Language Models](https://mlsanity.com/paper/2410.15364/) (2024) - [A Causal Adjustment Module for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2503.17862/) (2025) - [Neural Clustering based Visual Representation Learning](https://mlsanity.com/paper/2403.17409/) (2024) - [Universal Scene Graph Generation](https://mlsanity.com/paper/2503.15005/) (2025) - [Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation](https://mlsanity.com/paper/2409.10262/) (2024) - [Leveraging Predicate and Triplet Learning for Scene Graph Generation](https://mlsanity.com/paper/2406.02038/) (2024) - [Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection](https://mlsanity.com/paper/2403.14270/) (2024) - [Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene](https://mlsanity.com/paper/2503.15019/) (2025) - [Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency](https://mlsanity.com/paper/2405.12648/) (2024) - [Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2407.15396/) (2024) - [Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction](https://mlsanity.com/paper/2407.19259/) (2024) - [BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection](https://mlsanity.com/paper/2603.16645/) (2026) - [Learning Context-Conditioned Predicate Semantics via Prototype Feedback](https://mlsanity.com/paper/2605.29610/) (2026) ## Abstract (arXiv) Scene Graph Generation (SGG) aims to detect all the visual relation triplets in a given image. With the emergence of various advanced techniques for better utilizing both the intrinsic and extrinsic information in each relation triplet, SGG has achieved great progress over the recent years. However, due to the ubiquitous long-tailed predicate distributions, today's SGG models are still easily biased to the head predicates. Currently, the most prevalent debiasing solutions for SGG are re-balancing methods, eg, changing the distributions of original training samples. In this paper, we argue that all existing re-balancing strategies fail to increase the diversity of the relation triplet features of each predicate, which is critical for robust SGG. To this end, we propose a novel Compositional Feature Augmentation (CFA) strategy, which is the first unbiased SGG work to mitigate the bias issue from the perspective of increasing the diversity of triplet features. Specifically, we first decompose each relation triplet feature into two components: intrinsic feature and extrinsic feature, which correspond to the intrinsic characteristics and extrinsic contexts of a relation triplet, respectively. Then, we design two different feature augmentation modules to enrich the feature diversity of original relation triplets by replacing or mixing up either their intrinsic or extrinsic features from other samples. Due to its model-agnostic nature, CFA can be seamlessly incorporated into various SGG frameworks. Extensive ablations have shown that CFA achieves a new state-of-the-art performance on the trade-off between different metrics.