见树亦见林：重新思考弱监督医学视觉定位
Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
AI总结：
针对医学视觉定位中现有模型注意力低效、缺乏细粒度token表示的问题，提出疾病感知提示（DAP）过程，利用VLM可解释性图增强疾病区域特征并抑制背景，在三个胸部X光数据集上无额外像素注释时准确率提升20.74%。
摘要：
视觉定位（VG）是识别图像中与特定文本描述相关的特定区域的能力。在医学成像中，VG通过突出显示与文本描述对应的相关病理特征来增强可解释性，提高模型的透明度和可信度，以促进深度学习模型在临床实践中的更广泛采用。当前模型由于低效的注意力机制和缺乏细粒度的token表示，难以将文本描述与疾病区域关联起来。在本文中，我们通过实证展示了两个关键观察结果：首先，当前的视觉语言模型（VLMs）为背景token分配了高范数，分散了模型对疾病区域的注意力；其次，用于跨模态学习的全局token不能代表局部疾病token，这阻碍了文本与疾病token之间相关性的识别。为了解决这个问题，我们引入了简单但有效的疾病感知提示（DAP）过程，该过程使用VLM的可解释性图来识别适当的图像特征。这种简单的策略在放大疾病相关区域的同时抑制了背景干扰。在三个主要的胸部X光数据集上，DAP在不使用任何额外像素级注释的情况下，将视觉定位准确率提高了20.74%。
英文摘要：
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.
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。
