自信的多项选择学习
Confident Multiple Choice Learning
摘要：
可以说，包围方法是提高机器学习模型性能的最值得信赖的技术。依赖于朴素平均/投票方案的流行独立集成（IE）已经是涉及深度神经网络的大多数应用的典型选择，但是它们不考虑集成模型之间的高级协作。在本文中，我们提出了专门用于深度神经网络的新集成方法，称为置信多选择学习（CMCL）：它是多选择学习（MCL）的一种变体，通过解决其过度自信问题。特别地，除了原始MCL方案之外，CMCL的主要组件是（i）新损失，即，自信的预言丢失，（ii）新的体系结构，即，特征共享和（iii）新的训练方法，即，随机标记我们通过实验证明了CMCL在CIFAR和SVHN上的图像分类以及iCoseg上的前景-背景分割上的效果。特别是，CMCL使用5残差网络提供了14.05%和6.60%的相对减少前1出错率从相应的IE计划的分类任务CIFAR和SVHN，分别。
英文摘要：
Ensemble methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. Popular independent ensembles (IE) relying on naive averaging/voting scheme have been of typical choice for most applications involving deep neural networks, but they do not consider advanced collaboration among ensemble models. In this paper, we propose new ensemble methods specialized for deep neural networks, called confident multiple choice learning (CMCL): it is a variant of multiple choice learning (MCL) via addressing its overconfidence issue.In particular, the proposed major components of CMCL beyond the original MCL scheme are (i) new loss, i.e., confident oracle loss, (ii) new architecture, i.e., feature sharing and (iii) new training method, i.e., stochastic labeling. We demonstrate the effect of CMCL via experiments on the image classification on CIFAR and SVHN, and the foreground-background segmentation on the iCoseg. In particular, CMCL using 5 residual networks provides 14.05% and 6.60% relative reductions in the top-1 error rates from the corresponding IE scheme for the classification task on CIFAR and SVHN, respectively.
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。
