# LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray

arXiv: https://arxiv.org/abs/2603.19451 · HTML: https://mlsanity.com/paper/2603.19451/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [Detect Anything via Next Point Prediction](https://mlsanity.com/paper/2510.12798/) (2025)
- [Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation](https://mlsanity.com/paper/2403.08002/) (2024)
- [FLAIR: VLM with Fine-grained Language-informed Image Representations](https://mlsanity.com/paper/2412.03561/) (2024)
- [CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification](https://mlsanity.com/paper/2402.17417/) (2024)
- [LocCa: Visual Pretraining with Location-aware Captioners](https://mlsanity.com/paper/2403.19596/) (2024)
- [PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation](https://mlsanity.com/paper/2411.05085/) (2024)
- [BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature](https://mlsanity.com/paper/2501.07171/) (2025)
- [CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images](https://mlsanity.com/paper/2307.03293/) (2023)
- [Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment](https://mlsanity.com/paper/2303.07618/) (2023)
- [GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis](https://mlsanity.com/paper/2411.16778/) (2024)
- [RadVLM: A Multitask Conversational Vision-Language Model for Radiology](https://mlsanity.com/paper/2502.03333/) (2025)
- [ChEX: Interactive Localization and Region Description in Chest X-rays](https://mlsanity.com/paper/2404.15770/) (2024)
- [RadIR: A Scalable Framework for Multi-Grained Medical Image Retrieval via Radiology Report Mining](https://mlsanity.com/paper/2503.04653/) (2025)
- [Robust Detection Outcome: A Metric for Pathology Detection in Medical Images](https://mlsanity.com/paper/2303.01920/) (2023)
- [Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding](https://mlsanity.com/paper/2508.04572/) (2025)

## Abstract (arXiv)

Fine-grained representation learning is crucial for retrieval and phrase grounding in chest X-rays, where clinically relevant findings are often spatially confined. However, the lack of region-level supervision in contrastive models and the limited ability of large vision language models to capture fine-grained representations in external validation lead to suboptimal performance on these tasks. To address these limitations, we propose Location-aware Fine-grained representation learning (LoFi), which jointly optimizes sigmoid, captioning, and location-aware captioning losses using a lightweight large language model. The location-aware captioning loss enables region-level supervision through grounding and dense captioning objectives, thereby facilitating fine-grained representation learning. Building upon these representations, we integrate a fine-grained encoder into retrieval-based in-context learning to enhance chest X-ray grounding across diverse settings. Extensive experiments demonstrate that our method achieves superior retrieval and phrase grounding performance on MIMIC-CXR and PadChest-GR.