论文标题
局部对齐和统一性在医学图像上的对比度学习中的作用
The Role of Local Alignment and Uniformity in Image-Text Contrastive Learning on Medical Images
论文作者
论文摘要
事实证明，图像文本对比度学习对医学图像模型有效。当针对局部下游任务（例如语义分割或对象检测）时，将图像区域与句子相提并论的其他局部对比损失已显示出令人鼓舞的结果。我们研究当地对比度损失与全球（按样本）对比损失以及它们对局部医疗下游任务的影响如何相关的。基于理论比较，我们建议消除局部损失的某些组成部分，并用新的分布代替其他损失的成分，该分布在每个样本中实施了表示形式的统一性。我们在胸部X射线任务上进行了经验研究这种方法，并发现它非常有效，表现优于18个任务中的12项局部损失。
Image-text contrastive learning has proven effective for pretraining medical image models. When targeting localized downstream tasks like semantic segmentation or object detection, additional local contrastive losses that align image regions with sentences have shown promising results. We study how local contrastive losses are related to global (per-sample) contrastive losses and which effects they have on localized medical downstream tasks. Based on a theoretical comparison, we propose to remove some components of local losses and replace others by a novel distribution prior which enforces uniformity of representations within each sample. We empirically study this approach on chest X-ray tasks and find it to be very effective, outperforming methods without local losses on 12 of 18 tasks.
