# Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding

arXiv: https://arxiv.org/abs/2505.15123 · HTML: https://mlsanity.com/paper/2505.15123/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 73 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 30 of 56)

- [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)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology](https://mlsanity.com/paper/2301.02228/) (2023)
- [Grounding of Textual Phrases in Images by Reconstruction](https://mlsanity.com/paper/1511.03745/) (2015)
- [Contrastive Learning for Weakly Supervised Phrase Grounding](https://mlsanity.com/paper/2006.09920/) (2020)
- [Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction](https://mlsanity.com/paper/1806.03831/) (2018)
- [Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment](https://mlsanity.com/paper/1903.11649/) (2019)
- [Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation](https://mlsanity.com/paper/2007.01951/) (2020)
- [ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities](https://mlsanity.com/paper/2407.01525/) (2024)

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

- [A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling](https://mlsanity.com/paper/2602.22843/) (2026)
- [Multi-label Instance-level Generalised Visual Grounding in Agriculture](https://mlsanity.com/paper/2603.06699/) (2026)
- [OFBD: Object-Focused Background Debiasing for Long-Tailed Learning](https://mlsanity.com/paper/2609.37331/) (2026)

## Abstract (arXiv)

Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features corresponding to textual descriptions, improving model transparency and trustworthiness for wider adoption of deep learning models in clinical practice. Current models struggle to associate textual descriptions with disease regions due to inefficient attention mechanisms and a lack of fine-grained token representations. In this paper, we empirically demonstrate two key observations. First, current VLMs assign high norms to background tokens, diverting the model's attention from regions of disease. Second, the global tokens used for cross-modal learning are not representative of local disease tokens. This hampers identifying correlations between the text and disease tokens. To address this, we introduce simple, yet effective Disease-Aware Prompting (DAP) process, which uses the explainability map of a VLM to identify the appropriate image features. This simple strategy amplifies disease-relevant regions while suppressing background interference. Without any additional pixel-level annotations, DAP improves visual grounding accuracy by 20.74% compared to state-of-the-art methods across three major chest X-ray datasets.