发表机构
Cornell University; Weill Cornell Medicine（康奈尔大学; 威尔康奈尔医学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究诊断医学视觉上下文学习中的配对依赖性，提出晚期解配对课程（LUC）以调节该依赖性，在保持或提升匹配支持性能的同时缩小配对差距，并证明训练顺序对配对依赖性的关键影响。
AI 中文摘要
视觉上下文学习（ICL）非常适合标签稀缺的医学影像，它利用支持图像-标签对来演示输入-输出映射，而标签共同指示所请求的任务。我们通过一种测试时的错排（derangement）来诊断对单个配对的依赖性，该错排将每个支持标签重新分配给另一张支持图像，同时保持查询、支持图像和标签多重集不变。由此产生的配对差距（定义为打乱后减去匹配的性能）表明，所有四个已发布模型都依赖配对，但程度差异很大。对配对训练模型的进一步分析揭示了，即使使用真实、未修改的支持图像，也存在与支持相关的虚假区域和病灶大小偏差，以及对错误配准的支持标签的敏感性。为了调节这种依赖性，我们引入了一种晚期解配对课程（LUC），它从匹配训练开始，然后应用随机解配对，将每个支持标签替换为同一情节中另一支持图像的标签。LUC在两个骨干网络上几乎消除了配对差距，同时在所有评估的任务类型上保持或提高了匹配支持性能，其收益扩展到未见的任务和跨数据集情节。它还缓解了这些失败模式。在BraTS全肿瘤分割中，匹配支持的DSC从0.733上升到0.857，而差距从-0.184缩小到-0.008。在一个已发布的模型中，使用随机解配对进行简短微调减少了差距。一个反向课程将相同数量的解配对时期放在训练开始，却留下了很大的差距。这表明配对依赖性由训练顺序决定，而不仅仅由未配对训练的数量决定。
英文摘要
Visual in-context learning (ICL), well suited to label-scarce medical imaging, uses support image-label pairs to demonstrate input-output mappings, while the labels collectively indicate the requested task. We diagnose dependence on individual pairings with a test-time derangement that reassigns every support label to another support image while preserving the query, support images, and label multiset. The resulting pairing gap, defined as shuffled-minus-matched performance, shows that all four released models depend on the pairing, to widely varying degrees. Further analysis of a paired-trained model reveals support-associated spurious regions and lesion-size biases even with real, unaltered supports, alongside sensitivity to mis-registered support labels. To regulate this dependence, we introduce a late unpairing curriculum (LUC), which starts with matched training and then applies random unpairing, replacing each support label with that of another support in the same episode. LUC nearly closes the pairing gap on two backbones while maintaining or improving matched-support performance across all evaluated task types, with gains extending to held-out tasks and cross-dataset episodes. It also mitigates these failure modes. On BraTS whole-tumor segmentation, matched-support DSC rises from 0.733 to 0.857 while the gap shrinks from -0.184 to -0.008. In a released model, brief fine-tuning with random unpairing reduces the gap. A reversed curriculum that places the same number of unpairing epochs at the start of training leaves a large gap. This shows that pairing dependence is shaped by the order of training and not only by the amount of unpaired training.
Comments24 pages, 12 figures
