Back to the Source: Diffusion-Driven Test-Time Adaptation

Understand

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data.

• Existing methods update the source model by (re-)training on each target domain.
• While effective, re-training is sensitive to the amount and order of the data and the hyperparameters for optimization.
• We instead update the target data, by projecting all test inputs toward the source domain with a generative diffusion model.