# Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs

arXiv: https://arxiv.org/abs/2305.06343 · HTML: https://mlsanity.com/paper/2305.06343/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 85 of its 99 references that are in the map.
- First posted on arXiv 10 May 2023.

## Builds on (most cited first, 30 of 85)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)

## Built on by (most cited first, 30 of 39)

- [Compositional Chain-of-Thought Prompting for Large Multimodal Models](https://mlsanity.com/paper/2311.17076/) (2023)
- [Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models](https://mlsanity.com/paper/2305.19595/) (2023)
- [Revisiting the Role of Language Priors in Vision-Language Models](https://mlsanity.com/paper/2306.01879/) (2023)
- [Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning](https://mlsanity.com/paper/2406.15334/) (2024)
- [SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations](https://mlsanity.com/paper/2406.11171/) (2024)
- [Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding](https://mlsanity.com/paper/2306.08832/) (2023)
- [TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering](https://mlsanity.com/paper/2404.01476/) (2024)
- [VisMin: Visual Minimal-Change Understanding](https://mlsanity.com/paper/2407.16772/) (2024)
- [Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions](https://mlsanity.com/paper/2311.17048/) (2023)
- [Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models](https://mlsanity.com/paper/2308.09778/) (2023)
- [Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality](https://mlsanity.com/paper/2410.05210/) (2024)
- [VladVA: Discriminative Fine-tuning of LVLMs](https://mlsanity.com/paper/2412.04378/) (2024)
- [Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data](https://mlsanity.com/paper/2503.01167/) (2025)
- [Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features](https://mlsanity.com/paper/2412.00142/) (2024)
- [Removing Distributional Discrepancies in Captions Improves Image-Text Alignment](https://mlsanity.com/paper/2410.00905/) (2024)
- [Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales](https://mlsanity.com/paper/2404.11129/) (2024)
- [Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View](https://mlsanity.com/paper/2405.17201/) (2024)
- [Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions](https://mlsanity.com/paper/2407.06723/) (2024)
- [VSC: Visual Search Compositional Text-to-Image Diffusion Model](https://mlsanity.com/paper/2505.01104/) (2025)
- [Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection](https://mlsanity.com/paper/2403.14270/) (2024)
- [Relation Rectification in Diffusion Model](https://mlsanity.com/paper/2403.20249/) (2024)
- [LLaVA-SG: Leveraging Scene Graphs as Visual Semantic Expression in Vision-Language Models](https://mlsanity.com/paper/2408.16224/) (2024)
- [Causal Graphical Models for Vision-Language Compositional Understanding](https://mlsanity.com/paper/2412.09353/) (2024)
- [Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models](https://mlsanity.com/paper/2507.04976/) (2025)
- [Beyond Embeddings: The Promise of Visual Table in Visual Reasoning](https://mlsanity.com/paper/2403.18252/) (2024)
- [Generalized Unbiased Scene Graph Generation](https://mlsanity.com/paper/2308.04802/) (2023)
- [Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation](https://mlsanity.com/paper/2408.05456/) (2024)
- [SCRAMBLe : Enhancing Multimodal LLM Compositionality with Synthetic Preference Data](https://mlsanity.com/paper/2504.04740/) (2025)
- [Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions](https://mlsanity.com/paper/2510.16540/) (2025)
- [VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations](https://mlsanity.com/paper/2404.16365/) (2024)

## Abstract (arXiv)

Vision and language models (VLMs) have demonstrated remarkable zero-shot (ZS) performance in a variety of tasks. However, recent works have shown that even the best VLMs struggle to capture aspects of compositional scene understanding, such as object attributes, relations, and action states. In contrast, obtaining structured annotations, such as scene graphs (SGs), that could improve these models is time-consuming and costly, and thus cannot be used on a large scale. Here we ask whether small SG datasets can provide sufficient information for enhancing structured understanding of pretrained VLMs. We show that it is indeed possible to improve VLMs when learning from SGs by integrating components that incorporate structured information into both visual and textual representations. For the visual side, we incorporate a special "SG Component" in the image transformer trained to predict SG information, while for the textual side, we utilize SGs to generate fine-grained captions that highlight different compositional aspects of the scene. Our method improves the performance of several popular VLMs on multiple VL datasets with only a mild degradation in ZS capabilities.