Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various tasks. However, the conventional evaluation scheme used for deep active learning is below par. Current methods disregard some apparent parallel work in the closely related fields. Active learning methods are quite sensitive w.r.t. changes in the training procedure like data augmentation. They improve by a large-margin when integrated with semi-supervised learning, but barely perform better than the random baseline. We re-implement various latest active learning approaches for image classification and evaluate them under more realistic settings. We further validate our findings for semantic segmentation. Based on our observations, we realistically assess the current state of the field and propose a more suitable evaluation protocol.
翻译:积极学习的目的是降低大型数据集的机器学习模式培训所涉及的高标签成本,办法是高效地标出信息最丰富的样本。最近,深层积极学习在各种任务上表现出成功。然而,用于深层积极学习的常规评价计划低于平面。目前的方法忽视了密切相关领域某些明显的平行工作。积极学习方法在数据增强等培训程序中是相当敏感的变化。在与半监督学习相结合时,它们通过大边改进,但几乎不比随机基线好。我们重新采用各种最新的积极学习方法进行图像分类,并在更现实的环境下对其进行评估。我们进一步验证我们的结论,以便进行语义分化。根据我们的观察,我们现实地评估实地的现状,并提出更合适的评估程序。