Rethinking Generalization in Few-Shot Classification. (arXiv:2206.07267v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07267

Single image-level annotations only correctly describe an often small subset
of an image's content, particularly when complex real-world scenes are
depicted. While this might be acceptable in many classification scenarios, it
poses a significant challenge for applications where the set of classes differs
significantly between training and test time. In this paper, we take a closer
look at the implications in the context of $\textit{few-shot learning}$.
Splitting the input samples into patches and encoding these via the help of
Vision …

arxiv classification cv