arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.10467cs.CVcs.AIcs.LG
收藏

极小极大主动学习

Minimax Active Learning

UC Berkeley(加州大学伯克利分校)

Sayna Ebrahimi, William Gan, Dian Chen, Giscard Biamby, Kamyar Salahi, Michael Laielli, Shizhan Zhu, Trevor Darrell

摘要:

主动学习的目标是通过查询最具代表性的样本来开发标签效率算法,以供人类注释者标记。当前的主动学习技术要么依赖于模型不确定性来选择最不确定的样本,要么使用聚类或重构来选择最多样化的未标记样本集。虽然基于不确定性的策略容易受到离群值的影响,但仅仅依靠样本多样性并不能捕获主要任务的可用信息。在这项工作中,我们开发了一个半监督极大极小熵为基础的主动学习算法,利用不确定性和多样性的对抗方式。我们的模型由一个熵最小化特征编码网络和一个熵最大化分类层组成。这种极小极大公式减少了标记/未标记数据之间的分布差距,同时训练了一个训练器来区分标记/未标记数据。选择分类器中熵最高的样本进行标记,该分类器将其预测为未标记。我们在各种图像分类和语义分割基准数据集上评估了我们的方法,并显示出优于最先进方法的性能。

英文摘要:

Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. While uncertainty-based strategies are susceptible to outliers, solely relying on sample diversity does not capture the information available on the main task. In this work, we develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner. Our model consists of an entropy minimizing feature encoding network followed by an entropy maximizing classification layer. This minimax formulation reduces the distribution gap between the labeled/unlabeled data, while a discriminator is simultaneously trained to distinguish the labeled/unlabeled data. The highest entropy samples from the classifier that the discriminator predicts as unlabeled are selected for labeling. We evaluate our method on various image classification and semantic segmentation benchmark datasets and show superior performance over the state-of-the-art methods.

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。

↑