Fully Test-time Adaptation by Entropy Minimization

A model must adapt itself to generalize to new and different data during testing. This is the setting of fully test-time adaptation given only unlabeled test data and the model parameters. We propose test-time entropy minimization (tent) for adaptation: we optimize for model confidence as measured by the entropy of its predictions. During testing, we adapt the model features by estimating normalization statistics and optimizing channel-wise affine transformations. Tent improves robustness to corruptions for image classification on ImageNet and CIFAR-10/100 and achieves state-of-the-art error on ImageNet-C for ResNet-50. Tent demonstrates the feasibility of target-only domain adaptation for digit classification from SVHN to MNIST/MNIST-M/USPS and semantic segmentation from GTA to Cityscapes. Deep networks can achieve high accuracy on training and testing data from the same distribution, as evidenced by tremendous benchmark progress (Krizhevsky et al., 2012; Simonyan & Zisserman, 2015; He et al., 2016). However, generalization to new and different data is limited (Hendrycks & Dietterich, 2019; Recht et al., 2019; Geirhos et al., 2018). Accuracy suffers when the training (source) data differ from the testing (target) data, a condition known as dataset shift (Quionero-Candela et al., 2009). Models can be sensitive to shifts during testing that were not known during training, whether natural variations or corruptions, such as unexpected weather or sensor degradation.