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 2107.05445cs.CVcs.AIcs.LG
收藏

多领域学习中迁移与干扰的分离

Disentangling Transfer and Interference in Multi-Domain Learning

University of Rochester(罗切斯特大学);Rochester Institute of Technology(罗切斯特理工学院);Paige(Paige公司);Cornell Tech(康奈尔科技学院)

Yipeng Zhang, Tyler L. Hayes, Christopher Kanan

摘要:

人类非常善于将知识从一个领域转移到另一个领域,从而能够快速学习新任务。同样,迁移学习在使用预训练的许多计算机视觉问题中取得了巨大的成功。然而,在多域学习中,网络学习由不同数据集定义的多个任务,迁移的好处还没有得到充分的研究。学习多个域可能是有益的,或者在网络容量有限的情况下,这些域可能会相互干扰。理解不同容量的深度神经网络如何促进来自不同分布的输入之间的传输是迈向开放世界学习的关键一步。在这项工作中,我们破译的干扰和知识转移发生在多域学习的条件。我们提出了新的指标解开干扰和传输,建立实验协议,并检查网络容量,任务分组,和动态损失加权的作用,减少干扰,促进转让。

英文摘要:

Humans are incredibly good at transferring knowledge from one domain to another, enabling rapid learning of new tasks. Likewise, transfer learning has enabled enormous success in many computer vision problems using pretraining. However, the benefits of transfer in multi-domain learning, where a network learns multiple tasks defined by different datasets, has not been adequately studied. Learning multiple domains could be beneficial, or these domains could interfere with each other given limited network capacity. Understanding how deep neural networks of varied capacity facilitate transfer across inputs from different distributions is a critical step towards open world learning. In this work, we decipher the conditions where interference and knowledge transfer occur in multi-domain learning. We propose new metrics disentangling interference and transfer, set up experimental protocols, and examine the roles of network capacity, task grouping, and dynamic loss weighting in reducing interference and facilitating transfer.

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。

↑