Practical Transferability Estimation for Image Classification Tasks

arXiv:2106.10479v3 Announce Type: replace-cross
Abstract: Transferability estimation is an essential problem in transfer learning to predict how good the performance is when transferring a source model (or source task) to a target task. Recent analytical transferability metrics have been widely used for source model selection and multi-task learning. A major challenge is how to make transfereability estimation robust under the cross-domain cross-task settings. The recently proposed OTCE score solves this problem by considering both domain and task differences, with the …

abstract arxiv challenge classification cs.ai cs.cv cs.lg good image major metrics model selection multi-task learning performance practical tasks transfer transfer learning type