arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2002.12462cs.LGcs.CVstat.ML
收藏

LEEP:一种新的学习表征可迁移性评价方法

LEEP: A New Measure to Evaluate Transferability of Learned Representations

Amazon Web Services(亚马逊云服务);Facebook AI(Facebook 人工智能)

Cuong V. Nguyen, Tal Hassner, Matthias Seeger, Cedric Archambeau

摘要:

我们引入了一个新的措施来评估的可转移性表示学习分类。我们的衡量标准,对数预期经验预测(Log Expected Empirical Prediction,LEEP),简单且易于计算:当给定一个在源数据集上训练的分类器时,它只需要通过该分类器运行目标数据集一次。我们从理论上分析了LEEP的性质,并实证证明了其有效性。我们的分析表明,LEEP可以预测的性能和收敛速度的转移和Meta迁移学习方法,即使是小的或不平衡的数据。此外,LEEP优于最近提出的可转移性措施,如负条件熵和H分数。值得注意的是,当从ImageNet转移到CIFAR100时,LEEP在与实际转移准确性的相关性方面,与最佳竞争方法相比可以实现高达30%的改进。

英文摘要:

We introduce a new measure to evaluate the transferability of representations learned by classifiers. Our measure, the Log Expected Empirical Prediction (LEEP), is simple and easy to compute: when given a classifier trained on a source data set, it only requires running the target data set through this classifier once. We analyze the properties of LEEP theoretically and demonstrate its effectiveness empirically. Our analysis shows that LEEP can predict the performance and convergence speed of both transfer and meta-transfer learning methods, even for small or imbalanced data. Moreover, LEEP outperforms recently proposed transferability measures such as negative conditional entropy and H scores. Notably, when transferring from ImageNet to CIFAR100, LEEP can achieve up to 30% improvement compared to the best competing method in terms of the correlations with actual transfer accuracy.

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。

↑