论文标题
多样的合奏改善校准
Diverse Ensembles Improve Calibration
论文作者
论文摘要
现代深层神经网络可能会产生严格的校准预测，尤其是当火车和测试分布不匹配时。培训模型的合奏并平均他们的预测可以帮助减轻这些问题。我们提出了一种简单的技术来改善校准，使用每个集合成员的不同数据增强。此外，我们还使用“混合”未加强和增强输入的想法来改善测试和训练分布相同时的校准。这些简单的技术提高了CIFAR10和CIFAR100基准上强基线的校准和准确性，并提高了其损坏版本的域外数据。
Modern deep neural networks can produce badly calibrated predictions, especially when train and test distributions are mismatched. Training an ensemble of models and averaging their predictions can help alleviate these issues. We propose a simple technique to improve calibration, using a different data augmentation for each ensemble member. We additionally use the idea of `mixing' un-augmented and augmented inputs to improve calibration when test and training distributions are the same. These simple techniques improve calibration and accuracy over strong baselines on the CIFAR10 and CIFAR100 benchmarks, and out-of-domain data from their corrupted versions.
