Authors: Tonmoy Saikia,Thomas Brox,Cordelia Schmid
ArXiv: 2001.07926
Document:
PDF
DOI
Abstract URL: https://arxiv.org/abs/2001.07926v1
To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data as validation objective for hyper-parameter optimization (HPO) to improve on this goal. Given a rich enough search space, optimization of hyper-parameters learn features that maximize validation performance and, due to the objective, generalize across tasks and domains. We demonstrate the effectiveness of this strategy on few-shot image classification within and across domains. The learned features outperform all previous few-shot and meta-learning approaches.