Tent: Fully Test-Time Adaptation by Entropy Minimization

Dequan Wang · Evan Shelhamer · Shaoteng Liu · Bruno Olshausen · trevor darrell


Keywords: [ self-supervision ] [ domain adaptation ] [ robustness ] [ deep learning ] [ unsupervised learning ]

[ Abstract ]
[ Slides
[ Paper ]
Tue 4 May 9 a.m. PDT — 11 a.m. PDT
Spotlight presentation: Oral Session 7
Wed 5 May 3 a.m. PDT — 6:08 a.m. PDT


A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. Tent handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark. These results are achieved in one epoch of test-time optimization without altering training.

Chat is not available.