AEM：基于多示例学习的全切片图像分类的注意力熵最大化
AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification
AI总结：
针对多示例学习全切片图像分类中因注意力过度集中导致的过拟合问题，提出AEM正则化技术结合余弦权重退火惩罚注意力集中，在多种框架与机制下均取得卓越性能。
摘要：
多示例学习（MIL）能有效分析全切片图像，但因注意力过度集中而面临过拟合。现有方案依赖复杂的架构修改或额外处理步骤，我们提出注意力熵最大化（AEM），一种简单有效的正则化技术。研究发现注意力熵与模型性能呈正相关。基于此，我们将AEM正则化整合进MIL框架以惩罚过度的注意力集中。为解决对AEM权重参数的敏感性，我们采用余弦权重退火，降低参数依赖。广泛评估表明，AEM在多种特征提取器、MIL框架、注意力机制和数据增强技术上均表现出卓越性能。匿名代码：https://github.com/dazhangyu123/AEM。
英文摘要：
Multiple Instance Learning (MIL) effectively analyzes whole slide images but faces overfitting due to attention over-concentration. While existing solutions rely on complex architectural modifications or additional processing steps, we introduce Attention Entropy Maximization (AEM), a simple yet effective regularization technique. Our investigation reveals the positive correlation between attention entropy and model performance. Building on this insight, we integrate AEM regularization into the MIL framework to penalize excessive attention concentration. To address sensitivity to the AEM weight parameter, we implement Cosine Weight Annealing, reducing parameter dependency. Extensive evaluations demonstrate AEM's superior performance across diverse feature extractors, MIL frameworks, attention mechanisms, and augmentation techniques. Here is our anonymous code: https://github.com/dazhangyu123/AEM.
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。
