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 2104.07255cs.LGcs.CV
收藏

少样本学习仍然需要嵌入自适应

Embedding Adaptation is Still Needed for Few-Shot Learning

University of Southern California(南加州大学);Google AI(谷歌AI)

Sébastien M. R. Arnold, Fei Sha

摘要:

构建新的更具挑战性的任务集是分析和理解Few-Shot分类方法的有效方法。不幸的是,现有的构建这些任务集的方法有些不令人满意:它们要么假设训练和测试任务分布是相同的-这导致过于乐观的评估-或者采取“最坏情况”的哲学-这通常需要额外的人力劳动,如获得语义类关系。我们提出了ATG,一个原则性的聚类方法来定义训练和测试任务集,而无需额外的人类知识。ATG对任务分布进行训练和测试,同时要求它们共享预定义的信息量。我们经验证明了ATG在生成任务集,更容易,在两者之间,或更难比现有的基准,包括那些依赖于语义信息的有效性。最后,我们利用我们生成的任务集来阐明Few-Shot分类:基于梯度的方法-以前被认为表现不佳-在传输最具挑战性时可以胜过基于度量的方法。

英文摘要:

Constructing new and more challenging tasksets is a fruitful methodology to analyse and understand few-shot classification methods. Unfortunately, existing approaches to building those tasksets are somewhat unsatisfactory: they either assume train and test task distributions to be identical -- which leads to overly optimistic evaluations -- or take a "worst-case" philosophy -- which typically requires additional human labor such as obtaining semantic class relationships. We propose ATG, a principled clustering method to defining train and test tasksets without additional human knowledge. ATG models train and test task distributions while requiring them to share a predefined amount of information. We empirically demonstrate the effectiveness of ATG in generating tasksets that are easier, in-between, or harder than existing benchmarks, including those that rely on semantic information. Finally, we leverage our generated tasksets to shed a new light on few-shot classification: gradient-based methods -- previously believed to underperform -- can outperform metric-based ones when transfer is most challenging.

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。

↑