Testing-Time Adaptation through Online Normalization Estimation
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples. Known as Test-Time Adaptation, most prior work studying this task follows two assumptions in their evaluation where (1) test samples come together as a large batch, and (2) all from a single test distribution. However, in practice, these two assumptions may not stand, the reasons for which we propose two new evaluation settings where batch sizes are arbitrary and multiple distributions are considered. Unlike the previous methods that require a large batch of single distribution during test time to calculate stable batch-norm statistics, our method avoid any dependency on large online batches and is able to estimate accurate batch-norm statistics with a single sample. The proposed method significantly outperforms the State-Of-The-Art in the newly proposed settings in Test-Time Adaptation Task and also demonstrates improvements in various other settings such as Source-Free Unsupervised Domain Adaptation and Zero-Shot Classification.
PDF Abstract
CIFAR-10
ImageNet
CIFAR-100
MNIST
SVHN
STL-10
Stanford Cars
Food-101
ImageNet-C
