Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data. (arXiv:2311.01420v1 [cs.LG])

We propose a learning problem involving adapting a pre-trained source model
to the target domain for classifying all classes that appeared in the source
data, using target data that covers only a partial label space. This problem is
practical, as it is unrealistic for the target end-users to collect data for
all classes prior to adaptation. However, it has received limited attention in
the literature. To shed light on this issue, we construct benchmark datasets
and conduct extensive experiments to …

arxiv data domain fine-tuning practical source data space transfer