# VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval

arXiv: https://arxiv.org/abs/2505.20291 · HTML: https://mlsanity.com/paper/2505.20291/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models](https://mlsanity.com/paper/1411.2539/) (2014)
- [Benchmarking Representation Learning for Natural World Image Collections](https://mlsanity.com/paper/2103.16483/) (2021)
- [KNN-Diffusion: Image Generation via Large-Scale Retrieval](https://mlsanity.com/paper/2204.02849/) (2022)
- [Automatic Spatially-aware Fashion Concept Discovery](https://mlsanity.com/paper/1708.01311/) (2017)
- [E5-V: Universal Embeddings with Multimodal Large Language Models](https://mlsanity.com/paper/2407.12580/) (2024)
- [DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts](https://mlsanity.com/paper/2412.10510/) (2024)
- [MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models](https://mlsanity.com/paper/2410.08182/) (2024)
- [Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder](https://mlsanity.com/paper/2305.16304/) (2023)
- [Text encoders bottleneck compositionality in contrastive vision-language models](https://mlsanity.com/paper/2305.14897/) (2023)
- [INQUIRE: A Natural World Text-to-Image Retrieval Benchmark](https://mlsanity.com/paper/2411.02537/) (2024)
- [CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally](https://mlsanity.com/paper/2502.03566/) (2025)
- [Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond](https://mlsanity.com/paper/2402.10805/) (2024)
- [Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach](https://mlsanity.com/paper/2406.03411/) (2024)
- [Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries](https://mlsanity.com/paper/2502.16636/) (2025)
- [VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering](https://mlsanity.com/paper/2312.12273/) (2023)

## Built on by (most cited first, 3 of 3)

- [Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks](https://mlsanity.com/paper/2601.17644/) (2026)
- [Seeing Through Words: Controlling Visual Retrieval Quality with Language Models](https://mlsanity.com/paper/2602.21175/) (2026)
- [CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation](https://mlsanity.com/paper/2609.05518/) (2026)

## Abstract (arXiv)

Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such as pose and viewpoint. We proposeVisualize-then-Retrieve (VisRet), a retrieval paradigm that mitigates this limitation of cross-modal similarity alignment. VisRet first projects textual queries into the image modality via T2I generation, then performs retrieval within the image modality to bypass the weaknesses of cross-modal retrievers in recognizing subtle visual-spatial features. Across four benchmarks (Visual-RAG, INQUIRE-Rerank, Microsoft COCO, and our new Visual-RAG-ME featuring multi-entity comparisons), VisRet substantially outperforms cross-modal similarity matching and baselines that recast T2I retrieval as text-to-text similarity matching, improving nDCG@30 by 0.125 on average with CLIP as the retriever and by 0.121 with E5-V. For downstream question answering, VisRet increases accuracy on Visual-RAG and Visual-RAG-ME by 3.8% and 15.7% in top-1 retrieval, and by 3.9% and 11.1% in top-10 retrieval. Ablation studies show compatibility with different T2I instruction LLMs, T2I generation models, and downstream LLMs. VisRet provides a simple yet effective perspective for advancing in text-image retrieval. Our code and the new benchmark are publicly available at https://github.com/xiaowu0162/Visualize-then-Retrieve.