arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.07926cs.CV
收藏

跨领域Few-Shot分类的优化类属特征学习

Optimized Generic Feature Learning for Few-shot Classification across Domains

University of Freiburg(弗莱堡大学);Google Research(谷歌研究院)

Tonmoy Saikia, Thomas Brox, Cordelia Schmid

摘要:

学习跨任务和领域推广的模型或特征是机器学习的宏伟目标之一。在本文中,我们建议使用跨域,跨任务的数据作为验证目标的超参数优化(HPO),以提高这一目标。给定足够丰富的搜索空间,超参数的优化学习最大化验证性能的特征,并且由于目标,跨任务和域进行泛化。我们证明了这种策略的有效性Few-Shot图像分类内和跨域。学习的特征优于所有以前的Few-Shot和元学习方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑