Cross-domain Few-shot Meta-learning Using Stacking. (arXiv:2205.05831v1 [cs.CV])

Web: http://arxiv.org/abs/2205.05831

Cross-domain few-shot meta-learning (CDFSML) addresses learning problems
where knowledge needs to be transferred from several source domains into an
instance-scarce target domain with an explicitly different input distribution.
Recently published CDFSML methods generally construct a "universal model" that
combines knowledge of multiple source domains into one backbone feature
extractor. This enables efficient inference but necessitates re-computation of
the backbone whenever a new source domain is added. Moreover, state-of-the-art
methods derive their universal model from a collection of backbones -- normally …

arxiv cross cv learning meta meta-learning