主动学习是机器学习(更普遍的说是人工智能)的一个子领域,在统计学领域也叫查询学习、最优实验设计。“学习模块”和“选择策略”是主动学习算法的2个基本且重要的模块。 主动学习是“一种学习方法,在这种方法中,学生会主动或体验性地参与学习过程,并且根据学生的参与程度,有不同程度的主动学习。” (Bonwell&Eison 1991)Bonwell&Eison(1991) 指出:“学生除了被动地听课以外,还从事其他活动。” 在高等教育研究协会(ASHE)的一份报告中,作者讨论了各种促进主动学习的方法。他们引用了一些文献,这些文献表明学生不仅要做听,还必须做更多的事情才能学习。他们必须阅读,写作,讨论并参与解决问题。此过程涉及三个学习领域,即知识,技能和态度(KSA)。这种学习行为分类法可以被认为是“学习过程的目标”。特别是,学生必须从事诸如分析,综合和评估之类的高级思维任务。

VIP内容

尽管主动学习在图像识别方面取得了长足的进步,但仍然缺乏一种专门适用于目标检测的示例级的主动学习方法。在本文中,我们提出了多示例主动目标检测(MI-AOD),通过观察示例级的不确定性来选择信息量最大的图像用于检测器的训练。MI-AOD定义了示例不确定性学习模块,该模块利用在已标注集上训练的两个对抗性示例分类器的差异来预测未标注集的示例不确定性。MI-AOD将未标注的图像视为示例包,并将图像中的特征锚视为示例,并通过以多示例学习(MIL)方式对示例重加权的方法来估计图像的不确定性。反复进行示例不确定性的学习和重加权有助于抑制噪声高的示例,来缩小示例不确定性和图像级不确定性之间的差距。实验证明,MI-AOD为示例级的主动学习设置了坚实的基线。在常用的目标检测数据集上,MI-AOD和最新方法相比具有明显的优势,尤其是在已标注集很小的情况下。

代码地址为https://github.com/yuantn/MI-AOD

成为VIP会员查看完整内容
0
18

最新内容

In active learning, new labels are commonly acquired in batches. However, common acquisition functions are only meant for one-sample acquisition rounds at a time, and when their scores are used naively for batch acquisition, they result in batches lacking diversity, which deteriorates performance. On the other hand, state-of-the-art batch acquisition functions are costly to compute. In this paper, we present a novel class of stochastic acquisition functions that extend one-sample acquisition functions to the batch setting by observing how one-sample acquisition scores change as additional samples are acquired and modelling this difference for additional batch samples. We simply acquire new samples by sampling from the pool set using a Gibbs distribution based on the acquisition scores. Our acquisition functions are both vastly cheaper to compute and out-perform other batch acquisition functions.

0
0
下载
预览

最新论文

In active learning, new labels are commonly acquired in batches. However, common acquisition functions are only meant for one-sample acquisition rounds at a time, and when their scores are used naively for batch acquisition, they result in batches lacking diversity, which deteriorates performance. On the other hand, state-of-the-art batch acquisition functions are costly to compute. In this paper, we present a novel class of stochastic acquisition functions that extend one-sample acquisition functions to the batch setting by observing how one-sample acquisition scores change as additional samples are acquired and modelling this difference for additional batch samples. We simply acquire new samples by sampling from the pool set using a Gibbs distribution based on the acquisition scores. Our acquisition functions are both vastly cheaper to compute and out-perform other batch acquisition functions.

0
0
下载
预览
父主题
Top