论文标题
多视图数据的不确定性估计：查看整个图片的能力
Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture
论文作者
论文摘要
不确定性估计对于使神经网络在现实世界应用中值得信赖至关重要。已经进行了广泛的研究工作，以量化和减少预测性不确定性。但是，大多数现有作品都是为单峰数据而设计的，而多视图不确定性估计尚未得到充分研究。因此，我们提出了一个新的多视图分类框架，以进行更好的不确定性估计和室外样本检测，在该框架中，我们将每个视图与不确定性的分类器相关联，并以原则性的方式结合所有观点的预测。现实世界数据集的实验结果表明，我们提出的方法是一种准确，可靠且良好的分类器，这主要超过了根据预期校准误差，对噪声的稳健性，对局部样本分类和户外样品近距离样品检测任务的预期校准误差，噪声的鲁棒性以及准确性。
Uncertainty estimation is essential to make neural networks trustworthy in real-world applications. Extensive research efforts have been made to quantify and reduce predictive uncertainty. However, most existing works are designed for unimodal data, whereas multi-view uncertainty estimation has not been sufficiently investigated. Therefore, we propose a new multi-view classification framework for better uncertainty estimation and out-of-domain sample detection, where we associate each view with an uncertainty-aware classifier and combine the predictions of all the views in a principled way. The experimental results with real-world datasets demonstrate that our proposed approach is an accurate, reliable, and well-calibrated classifier, which predominantly outperforms the multi-view baselines tested in terms of expected calibration error, robustness to noise, and accuracy for the in-domain sample classification and the out-of-domain sample detection tasks.
