On Transfer in Classification: How Well do Subsets of Classes Generalize?

arXiv:2403.03569v1 Announce Type: new
Abstract: In classification, it is usual to observe that models trained on a given set of classes can generalize to previously unseen ones, suggesting the ability to learn beyond the initial task. This ability is often leveraged in the context of transfer learning where a pretrained model can be used to process new classes, with or without fine tuning. Surprisingly, there are a few papers looking at the theoretical roots beyond this phenomenon. In this work, …

abstract arxiv beyond classification context cs.cv cs.lg learn observe set subsets transfer transfer learning type