论文标题
一项关于深度积极学习图像分类功效的实证研究
An Empirical Study on the Efficacy of Deep Active Learning for Image Classification
论文作者
论文摘要
深入的积极学习（DAL）已被提倡作为降低监督学习中标签成本的一种有前途的方法。但是，对DAL方法的现有评估是基于不同的设置，其结果是有争议的。为了解决这个问题，本文全面评估了19种在均匀设置中的现有DAL方法，包括传统的完全 - \下划线{s} Upervised \ Uperline \ undustline {a} ctive \ contline {l} resisning {l} ginning（sal）策略和Emerging \ superline {s} emi-\ supperline {s} emi-\ supperline {s} \下划线{l}收入（SSAL）技术。我们有几个非平凡的发现。首先，大多数SAL方法无法获得比随机选择更高的精度。其次，与纯SAL方法相比，半监督训练可以显着提高性能。第三，在SSAL设置中执行数据选择可以实现显着且一致的性能改善，尤其是使用丰富的未标记数据。我们的发现为从业人员提供了以下指南：（i）提早应用SSAL和（ii）尽可能收集更多未标记的数据，以获得更好的模型性能。
Deep Active Learning (DAL) has been advocated as a promising method to reduce labeling costs in supervised learning. However, existing evaluations of DAL methods are based on different settings, and their results are controversial. To tackle this issue, this paper comprehensively evaluates 19 existing DAL methods in a uniform setting, including traditional fully-\underline{s}upervised \underline{a}ctive \underline{l}earning (SAL) strategies and emerging \underline{s}emi-\underline{s}upervised \underline{a}ctive \underline{l}earning (SSAL) techniques. We have several non-trivial findings. First, most SAL methods cannot achieve higher accuracy than random selection. Second, semi-supervised training brings significant performance improvement compared to pure SAL methods. Third, performing data selection in the SSAL setting can achieve a significant and consistent performance improvement, especially with abundant unlabeled data. Our findings produce the following guidance for practitioners: one should (i) apply SSAL early and (ii) collect more unlabeled data whenever possible, for better model performance.
