# Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation

arXiv: https://arxiv.org/abs/2005.08230 · HTML: https://mlsanity.com/paper/2005.08230/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2020.

## Built on by (most cited first, 30 of 31)

- [Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2104.00308/) (2021)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [Energy-Based Learning for Scene Graph Generation](https://mlsanity.com/paper/2103.02221/) (2021)
- [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021)
- [Scene Graph Generation: A Comprehensive Survey](https://mlsanity.com/paper/2201.00443/) (2022)
- [Recovering the Unbiased Scene Graphs from the Biased Ones](https://mlsanity.com/paper/2107.02112/) (2021)
- [The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation](https://mlsanity.com/paper/2206.03014/) (2022)
- [Fully Convolutional Scene Graph Generation](https://mlsanity.com/paper/2103.16083/) (2021)
- [Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning](https://mlsanity.com/paper/2208.08165/) (2022)
- [Segmentation-grounded Scene Graph Generation](https://mlsanity.com/paper/2104.14207/) (2021)
- [Devil's on the Edges: Selective Quad Attention for Scene Graph Generation](https://mlsanity.com/paper/2304.03495/) (2023)
- [NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation](https://mlsanity.com/paper/2207.13316/) (2022)
- [Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network](https://mlsanity.com/paper/2212.00443/) (2022)
- [Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery](https://mlsanity.com/paper/2404.00756/) (2024)
- [Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2208.03763/) (2022)
- [DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation](https://mlsanity.com/paper/2503.13957/) (2025)
- [Rethinking the Evaluation of Unbiased Scene Graph Generation](https://mlsanity.com/paper/2208.01909/) (2022)
- [Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection](https://mlsanity.com/paper/2403.14270/) (2024)
- [Psychologically-Inspired, Unsupervised Inference of Perceptual Groups of GUI Widgets from GUI Images](https://mlsanity.com/paper/2206.10352/) (2022)
- [PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks](https://mlsanity.com/paper/2504.00844/) (2025)
- [Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency](https://mlsanity.com/paper/2405.12648/) (2024)
- [Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention](https://mlsanity.com/paper/2211.06027/) (2022)
- [ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery](https://mlsanity.com/paper/2406.06028/) (2024)
- [Vision Language Models Cannot Plan, but Can They Formalize?](https://mlsanity.com/paper/2509.21576/) (2025)
- [RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation](https://mlsanity.com/paper/2309.03240/) (2023)
- [Zero-Shot Scene Graph Generation via Triplet Calibration and Reduction](https://mlsanity.com/paper/2309.03542/) (2023)
- [SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering](https://mlsanity.com/paper/2310.01842/) (2023)
- [SG-Shuffle: Multi-aspect Shuffle Transformer for Scene Graph Generation](https://mlsanity.com/paper/2211.04773/) (2022)
- [SGTR+: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2401.12835/) (2024)
- [SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation](https://mlsanity.com/paper/2211.16697/) (2022)

## Abstract (arXiv)

Scene graph generation (SGG) aims to predict graph-structured descriptions of input images, in the form of objects and relationships between them. This task is becoming increasingly useful for progress at the interface of vision and language. Here, it is important - yet challenging - to perform well on novel (zero-shot) or rare (few-shot) compositions of objects and relationships. In this paper, we identify two key issues that limit such generalization. Firstly, we show that the standard loss used in this task is unintentionally a function of scene graph density. This leads to the neglect of individual edges in large sparse graphs during training, even though these contain diverse few-shot examples that are important for generalization. Secondly, the frequency of relationships can create a strong bias in this task, such that a blind model predicting the most frequent relationship achieves good performance. Consequently, some state-of-the-art models exploit this bias to improve results. We show that such models can suffer the most in their ability to generalize to rare compositions, evaluating two different models on the Visual Genome dataset and its more recent, improved version, GQA. To address these issues, we introduce a density-normalized edge loss, which provides more than a two-fold improvement in certain generalization metrics. Compared to other works in this direction, our enhancements require only a few lines of code and no added computational cost. We also highlight the difficulty of accurately evaluating models using existing metrics, especially on zero/few shots, and introduce a novel weighted metric.