# Adding simple structure at inference improves Vision-Language Compositionality

arXiv: https://arxiv.org/abs/2506.09691 · HTML: https://mlsanity.com/paper/2506.09691/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 31 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 27 of 27)

- [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)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (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)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts](https://mlsanity.com/paper/2111.08276/) (2021)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining](https://mlsanity.com/paper/2204.14095/) (2022)
- [Does CLIP Bind Concepts? Probing Compositionality in Large Image Models](https://mlsanity.com/paper/2212.10537/) (2022)
- [Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem](https://mlsanity.com/paper/2411.00238/) (2024)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [Image-text Retrieval: A Survey on Recent Research and Development](https://mlsanity.com/paper/2203.14713/) (2022)
- [Equivariant Similarity for Vision-Language Foundation Models](https://mlsanity.com/paper/2303.14465/) (2023)
- [Revisiting the Role of Language Priors in Vision-Language Models](https://mlsanity.com/paper/2306.01879/) (2023)
- [Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality](https://mlsanity.com/paper/2211.00768/) (2022)
- [Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings](https://mlsanity.com/paper/2404.16820/) (2024)
- [Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining](https://mlsanity.com/paper/2311.03964/) (2023)
- [Natural Language Inference Improves Compositionality in Vision-Language Models](https://mlsanity.com/paper/2410.22315/) (2024)
- [BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval](https://mlsanity.com/paper/2406.09952/) (2024)

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

- [Half-Truths Break Similarity-Based Retrieval](https://mlsanity.com/paper/2602.23906/) (2026)

## Abstract (arXiv)

Dual encoder Vision-Language Models (VLM) such as CLIP are widely used for image-text retrieval tasks. However, those models struggle with compositionality, showing a bag-of-words-like behavior that limits their retrieval performance. Many different training approaches have been proposed to improve the vision-language compositionality capabilities of those models. In comparison, inference-time techniques have received little attention. In this paper, we propose to add simple structure at inference, where, given an image and a caption: i) we divide the image into different smaller crops, ii) we extract text segments, capturing objects, attributes and relations, iii) using a VLM, we find the image crops that better align with text segments obtaining matches, and iv) we compute the final image-text similarity aggregating the individual similarities of the matches. Based on various popular dual encoder VLMs, we evaluate our approach in controlled and natural datasets for VL compositionality. We find that our approach consistently improves the performance of evaluated VLMs without any training, which shows the potential of inference-time techniques. The results are especially good for attribute-object binding as shown in the controlled dataset. As a result of an extensive analysis: i) we show that processing image crops is actually essential for the observed gains in performance, and ii) we identify specific areas to further improve inference-time approaches.