arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.09890cs.CV
收藏

监督级别量表(SLS)

Supervision Levels Scale (SLS)

University of Bristol(布里斯托大学)

Dima Damen, Michael Wray

摘要:

我们提出了一个三维离散和增量尺度来编码方法的监督级别-即训练模型以实现给定性能时使用的数据和标签。我们捕获了监督的三个方面,已知这些方面在需要额外成本的同时为方法提供了优势:预训练,训练标签和训练数据。所提出的三维量表可以包含在结果表或排行榜中,以便不仅通过其性能,而且还通过每种方法所使用的数据监督水平来方便地比较方法。监督水平量表(SLS)首先针对任何任务/数据集/挑战提出。然后将其应用于EPIC-KITCHENS-100数据集,用于与该数据集相关的各种排行榜和挑战。

英文摘要:

We propose a three-dimensional discrete and incremental scale to encode a method's level of supervision - i.e. the data and labels used when training a model to achieve a given performance. We capture three aspects of supervision, that are known to give methods an advantage while requiring additional costs: pre-training, training labels and training data. The proposed three-dimensional scale can be included in result tables or leaderboards to handily compare methods not only by their performance, but also by the level of data supervision utilised by each method. The Supervision Levels Scale (SLS) is first presented generally fo any task/dataset/challenge. It is then applied to the EPIC-KITCHENS-100 dataset, to be used for the various leaderboards and challenges associated with this dataset.

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。

↑