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’unaugmented 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.
|Number of pages||6|
|Publication status||Published - 17 Jul 2020|
|Event||ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning - Virtual workshop|
Duration: 17 Jul 2020 → 17 Jul 2020
|Workshop||ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning|
|Abbreviated title||ICML UDL 2020|
|Period||17/07/20 → 17/07/20|