Generate to Ground: Multimodal Text Conditioning Boosts Phrase Grounding in Medical Vision-Language Models

Felix Nützel, Mischa Dombrowski, Bernhard Kainz

Keywords: Phrase Grounding, Visual Grounding, Stable Diffusion, Latent Diffusion Models, Cross-Attention, Chest X-Rays

Abstract:

Phrase grounding, i.e., mapping natural language phrases to specific image regions, holds significant potential for disease localization in medical imaging through clinical reports. While current state-of-the-art methods rely on discriminative, self-supervised contrastive models, we demonstrate that generative text-to-image diffusion models, leveraging cross-attention maps, can achieve superior zero-shot phrase grounding performance. Contrary to prior assumptions, we show that fine-tuning diffusion models with a frozen, domain-specific language model, such as CXR-BERT, substantially outperforms domain-agnostic counterparts. This setup achieves remarkable improvements, with mIoU scores doubling those of current discriminative methods. These findings highlight the underexplored potential of generative models for phrase grounding tasks. To further enhance performance, we introduce Bimodal Bias Merging (BBM), a novel post-processing technique that aligns text and image biases to identify regions of high certainty. BBM refines cross-attention maps, achieving even greater localization accuracy. Our results establish generative approaches as a more effective paradigm for phrase grounding in the medical imaging domain, paving the way for more robust and interpretable applications in clinical practice. The source code and model weights are available at https://github.com/Felix-012/generate_to_ground.

Primary Subject Area: Interpretability and Explainable AI

Secondary Subject Area: Generative Models

Paper Type: Both

Registration Requirement: Yes

Reproducibility: https://github.com/Felix-012/generate_to_ground

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Created a single midl25_NNN.zip file with midl25_NNN.tex, midl25_NNN.bib, all necessary figures and files., Includes \documentclass{midl}, \jmlryear{2025}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package, Did not use the times package., Author and institution details are de-anonymized where needed. All author names, affiliations, and paper title are correctly spelled and capitalized in the biography section., References must use the .bib file. Did not override the bibliographystyle defined in midl.cls. Did not use \begin{thebibliography} directly to insert references., Tables and figures do not overflow margins; avoid using \scalebox; used \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., Appendices and supplementary material are included in the same PDF after references., Main paper does not exceed 9 pages; acknowledgements, references, and appendix start on page 10 or later.

Submission Number: 36