论文标题
在多样性正则化的合奏中提高鲁棒性和校准
Improving robustness and calibration in ensembles with diversity regularization
论文作者
论文摘要
校准和不确定性估计是高危环境中的关键主题。我们为分类任务引入了新的多样性正常化程序，该任务使用分布样本，并提高合奏的总体准确性，校准和分布外检测功能。在最近对合奏多样性的兴趣之后，我们系统地评估了明确规范整体多样性的生存能力，以改善分布数据以及数据集偏移的校准。我们证明，多样性正则化在体系结构中非常有益，在体系结构中，在个人成员之间部分共享权重，甚至允许更少的合奏成员达到相同水平的鲁棒性。 CIFAR-10，CIFAR-100和SVHN上的实验表明，正规化多样性可以对校准和鲁棒性以及分布外检测产生重大影响。
Calibration and uncertainty estimation are crucial topics in high-risk environments. We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples and increases the overall accuracy, calibration and out-of-distribution detection capabilities of ensembles. Following the recent interest in the diversity of ensembles, we systematically evaluate the viability of explicitly regularizing ensemble diversity to improve calibration on in-distribution data as well as under dataset shift. We demonstrate that diversity regularization is highly beneficial in architectures, where weights are partially shared between the individual members and even allows to use fewer ensemble members to reach the same level of robustness. Experiments on CIFAR-10, CIFAR-100, and SVHN show that regularizing diversity can have a significant impact on calibration and robustness, as well as out-of-distribution detection.
