arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04061cs.LGcs.AI
收藏

基于高斯过程的概率注意深度多实例学习

Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning

University of Granada(格拉纳达大学)

Arne Schmidt, Pablo Morales-Álvarez, Rafael Molina

摘要:

多实例学习(MIL)是一种弱监督学习范式,由于它比完全监督方法需要更少的标记工作,因此变得越来越流行。这对于创建大型注释数据集仍然具有挑战性的领域尤其有趣,例如医学领域。尽管最近的深度学习MIL方法已经获得了最先进的结果,但它们是完全确定性的,并且不提供预测的不确定性估计。在这项工作中,我们引入了注意力高斯过程(AGP)模型,这是一种基于高斯过程的新型概率注意力机制。AGP提供了准确的袋级预测以及实例级可解释性,并且可以端到端地进行训练。此外,它的概率性质保证了对小数据集上的过拟合和预测的不确定性估计的鲁棒性。后者在医疗应用中尤为重要,因为决策对患者的健康有直接影响。所提出的模型进行了实验验证如下。首先,它的行为说明在两个合成MIL实验的基础上著名的MNIST和CIFAR-10数据集,分别。然后,在三个不同的现实世界癌症检测实验中进行评估。AGP优于最先进的MIL方法,包括确定性深度学习方法。它甚至在小于100个标签的小数据集上也表现出强大的性能,并且在外部测试集上比竞争方法更好地推广。此外,我们的实验表明,预测的不确定性与错误预测的风险相关,因此它是一个很好的指标,在实践中的可靠性。我们的代码是公开的。

英文摘要:

Multiple Instance Learning (MIL) is a weakly supervised learning paradigm that is becoming increasingly popular because it requires less labeling effort than fully supervised methods. This is especially interesting for areas where the creation of large annotated datasets remains challenging, as in medicine. Although recent deep learning MIL approaches have obtained state-of-the-art results, they are fully deterministic and do not provide uncertainty estimations for the predictions. In this work, we introduce the Attention Gaussian Process (AGP) model, a novel probabilistic attention mechanism based on Gaussian Processes for deep MIL. AGP provides accurate bag-level predictions as well as instance-level explainability, and can be trained end-to-end. Moreover, its probabilistic nature guarantees robustness to overfitting on small datasets and uncertainty estimations for the predictions. The latter is especially important in medical applications, where decisions have a direct impact on the patient's health. The proposed model is validated experimentally as follows. First, its behavior is illustrated in two synthetic MIL experiments based on the well-known MNIST and CIFAR-10 datasets, respectively. Then, it is evaluated in three different real-world cancer detection experiments. AGP outperforms state-of-the-art MIL approaches, including deterministic deep learning ones. It shows a strong performance even on a small dataset with less than 100 labels and generalizes better than competing methods on an external test set. Moreover, we experimentally show that predictive uncertainty correlates with the risk of wrong predictions, and therefore it is a good indicator of reliability in practice. Our code is publicly available.

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。

↑