# Measuring Image-Relation Alignment: Reference-Free Evaluation of VLMs and Synthetic Pre-training for Open-Vocabulary Scene Graph Generation

arXiv: https://arxiv.org/abs/2509.01209 · HTML: https://mlsanity.com/paper/2509.01209/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [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)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)
- [Learning to Detect Human-Object Interactions](https://mlsanity.com/paper/1702.05448/) (2017)
- [Panoptic Scene Graph Generation](https://mlsanity.com/paper/2207.11247/) (2022)
- [The All-Seeing Project V2: Towards General Relation Comprehension of the Open World](https://mlsanity.com/paper/2402.19474/) (2024)
- [RegionGPT: Towards Region Understanding Vision Language Model](https://mlsanity.com/paper/2403.02330/) (2024)
- [Fine-Grained Scene Graph Generation with Data Transfer](https://mlsanity.com/paper/2203.11654/) (2022)
- [Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning](https://mlsanity.com/paper/2208.08165/) (2022)
- [RLIPv2: Fast Scaling of Relational Language-Image Pre-training](https://mlsanity.com/paper/2308.09351/) (2023)
- [Large-Scale Visual Relationship Understanding](https://mlsanity.com/paper/1804.10660/) (2018)
- [LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation](https://mlsanity.com/paper/2310.10404/) (2023)
- [Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention](https://mlsanity.com/paper/2311.10988/) (2023)
- [Transforming Visual Scene Graphs to Image Captions](https://mlsanity.com/paper/2305.02177/) (2023)
- [OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics](https://mlsanity.com/paper/2202.10201/) (2022)
- [Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection](https://mlsanity.com/paper/2403.14270/) (2024)
- [Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation](https://mlsanity.com/paper/2305.18668/) (2023)

## Built on by (most cited first, 1 of 1)

- [SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions](https://mlsanity.com/paper/2609.31823/) (2026)

## Abstract (arXiv)

Scene Graph Generation (SGG) encodes visual relationships between objects in images as graph structures. Thanks to the advances of Vision-Language Models (VLMs), the task of Open-Vocabulary SGG has been recently proposed where models are evaluated on their functionality to learn a wide and diverse range of relations. Current benchmarks in SGG, however, possess a very limited vocabulary, making the evaluation of open-source models inefficient. In this paper, we propose a new reference-free metric to fairly evaluate the open-vocabulary capabilities of VLMs for relation prediction. Another limitation of Open-Vocabulary SGG is the reliance on weakly supervised data of poor quality for pre-training. We also propose a new solution for quickly generating high-quality synthetic data through region-specific prompt tuning of VLMs. Experimental results show that pre-training with this new data split can benefit the generalization capabilities of Open-Voc SGG models.