LoFi：面向胸部X光的基于位置的细粒度表示学习
LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray
AI总结：
本文提出LoFi，通过联合优化sigmoid、标注和位置感知标注损失，提升胸部X光的检索和短语接地性能，实验表明在MIMIC-CXR和PadChest-GR数据集上表现优异。
摘要：
细粒度表示学习对于胸部X光的检索和短语接地至关重要，其中临床相关发现常空间受限。然而，对比模型缺乏区域级监督以及大视觉语言模型在外部验证中捕捉细粒度表示的能力有限，导致这些任务性能不佳。为解决这些问题，我们提出位置感知细粒度表示学习（LoFi），利用轻量级大语言模型联合优化sigmoid、标注和位置感知标注损失。位置感知标注损失通过接地和密集标注目标实现区域级监督，从而促进细粒度表示学习。基于这些表示，我们整合细粒度编码器到基于检索的上下文学习中，以增强胸部X光的接地能力。大量实验表明，我们的方法在MIMIC-CXR和PadChest-GR数据集上实现了更优的检索和短语接地性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
