Abstract | ||
---|---|---|
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): 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 shows the feasibility of target-only domain adaptation for digit classification from SVHN to MNIST/MNIST-M/USPS and semantic segmentation from GTA to Cityscapes. |
Year | Venue | DocType |
---|---|---|
2021 | ICLR | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dequan Wang | 1 | 0 | 0.34 |
Evan Shelhamer | 2 | 4624 | 198.38 |
Shaoteng Liu | 3 | 24 | 1.34 |
Bruno A. Olshausen | 4 | 493 | 66.79 |
Trevor Darrell | 5 | 22413 | 1800.67 |