Deep Active Learning over the Long Tail
Deep Active Learning over the Long Tail
复制标题
长尾深度主动学习
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Ran El
中科院分区：
文献类型：
--
作者：
Yonatan Geifman;Ran El
本文关注深度神经网络的基于池的主动学习。受coreset数据集压缩思想的启发，我们提出了一种新的主动学习算法，该算法在表示层上的神经激活空间中使用最远优先遍历从池中查询连续点。对于三个数据集：MNIST，CIFAR-10和CIFAR-100，我们在被动学习（随机采样）的样本复杂性方面表现出一致和压倒性的改善。此外，我们的算法优于传统的不确定性采样技术（使用softmax激活获得），并且我们确定了不确定性采样仅略优于随机采样的情况。
This paper is concerned with pool-based active learning for deep neural networks. Motivated by coreset dataset compression ideas, we present a novel active learning algorithm that queries consecutive points from the pool using farthest-first traversals in the space of neural activation over a representation layer. We show consistent and overwhelming improvement in sample complexity over passive learning (random sampling) for three datasets: MNIST, CIFAR-10, and CIFAR-100. In addition, our algorithm outperforms the traditional uncertainty sampling technique (obtained using softmax activations), and we identify cases where uncertainty sampling is only slightly better than random sampling.