Classical Sequence Match is a Competitive Few-Shot One-Class Learner. (arXiv:2209.06394v2 [cs.LG] UPDATED)

Nowadays, transformer-based models gradually become the default choice for
artificial intelligence pioneers. The models also show superiority even in the
few-shot scenarios. In this paper, we revisit the classical methods and propose
a new few-shot alternative. Specifically, we investigate the few-shot one-class
problem, which actually takes a known sample as a reference to detect whether
an unknown instance belongs to the same class. This problem can be studied from
the perspective of sequence match. It is shown that with meta-learning, …

arxiv