arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.02653cs.LGcs.CVstat.ML
收藏

小样本机器学习研究综述

A Survey on Machine Learning from Few Samples

Tsinghua University(清华大学);Didi Research Institute, Didi Chuxing(滴滴出行滴滴研究院);Didi AI Labs(滴滴人工智能实验室);University of Michigan, Ann Arbor(密歇根大学安娜堡分校);University of Hamburg(汉堡大学)

Jiang Lu, Pinghua Gong, Jieping Ye, Jianwei Zhang, Changshui Zhang

摘要:

小样本学习是机器学习领域的一个重要而又具有挑战性的问题。成功地从非常少的样本中学习和概括的能力是区分人工智能和人类智能的显著分界线,因为人类可以容易地从单个或少数几个示例中建立他们对新颖性的认知,而机器学习算法通常需要数百或数千个监督样本来保证概括能力。尽管FSL的历史可以追溯到21世纪初,近年来随着深度学习技术的蓬勃发展而受到广泛关注,但到目前为止,FSL的调查或评论很少。在这种情况下,我们广泛审查了2000年代至2019年的300多篇FSL论文,并为FSL提供了及时和全面的调查。本文回顾了FSL的发展历史和研究现状,将FSL方法原则上分为基于生成模型的FSL方法和基于判别模型的FSL方法,重点介绍了基于元学习的FSL方法。本文还总结了近年来出现的几个FSL的外延问题,并对这些问题的最新进展进行了综述。最后,总结了FSL在计算机视觉、自然语言处理、音频和语音、强化学习和机器人、数据分析等领域的应用,并对未来的发展趋势进行了展望。

英文摘要:

Few sample learning (FSL) is significant and challenging in the field of machine learning. The capability of learning and generalizing from very few samples successfully is a noticeable demarcation separating artificial intelligence and human intelligence since humans can readily establish their cognition to novelty from just a single or a handful of examples whereas machine learning algorithms typically entail hundreds or thousands of supervised samples to guarantee generalization ability. Despite the long history dated back to the early 2000s and the widespread attention in recent years with booming deep learning technologies, little surveys or reviews for FSL are available until now. In this context, we extensively review 300+ papers of FSL spanning from the 2000s to 2019 and provide a timely and comprehensive survey for FSL. In this survey, we review the evolution history as well as the current progress on FSL, categorize FSL approaches into the generative model based and discriminative model based kinds in principle, and emphasize particularly on the meta learning based FSL approaches. We also summarize several recently emerging extensional topics of FSL and review the latest advances on these topics. Furthermore, we highlight the important FSL applications covering many research hotspots in computer vision, natural language processing, audio and speech, reinforcement learning and robotic, data analysis, etc. Finally, we conclude the survey with a discussion on promising trends in the hope of providing guidance and insights to follow-up researches.

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。

↑