The settings of continual test-time domain adaptation about test-time-adaptation HOT 2 CLOSED

Hi @Bojian-Chen,

as described in our paper, we are looking at a broader range of practical applications: the common source-free setting (indicated by the source-free column in our result tables) and a setting where source data (or at least a small fraction of it, like 1%) may be available. If source data is available, source replay can be run as a simple extension. For warm-up, analogous to EATA (https://arxiv.org/abs/2204.02610), an out-of-distribution detection can be performed to collect some in-distribution data. The prototypes do not need access to source data, but can come together with an arbitrary model independent of its pre-training. A similar assumption is also made in the paper (https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136930433.pdf). The test phase is source-free in the latter two cases. You can see the results of the individual settings in our component analysis in Table 4. I hope this helps!

Kind regards,
Mario

from test-time-adaptation.

Hi, Thank you for your prompt and patient response!
I have a basic question:
Is the main difference between test-time adaptation and sourece-free domain adaptation in the testing phase, where test-time domain adaptation is trested after only one training epoch?

from test-time-adaptation.