Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification-猫眼课题宝

DOI：

10.1007/978-3-030-59710-8_36

发表时间：

2020-07

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Pengyu Yuan;Aryan Mobiny;J. Jahanipour;Xiaoyang Li;P. Cicalese;B. Roysam;Vishal M. Patel;Maric Dragan;H. Nguyen

深度神经网络（或DNN）必须在感兴趣的任务或数据收集协议发生变化时不断科普输入数据的分布变化。从头开始重新训练网络来解决这个问题会带来巨大的成本。元学习旨在提供一个自适应模型，该模型对这些底层分布变化敏感，但在元训练过程中需要执行许多任务。在本文中，我们提出了一种tAsk-auGmented actIve meta learning（AGILE）方法，通过使用少量的训练示例来有效地使DNN适应新任务。AGILE将元学习算法与一种新的任务增强技术相结合，我们使用该技术来生成初始自适应模型。然后，当更新模型到新任务时，它使用贝叶斯丢弃不确定性估计来主动选择最困难的样本。这使得AGILE可以用更少的任务和一些信息样本进行学习，从而在有限的数据集上实现高性能。我们使用脑细胞分类任务进行实验，并将结果与从头开始训练的普通元学习模型进行比较。我们表明，所提出的任务增强元学习框架可以学习分类新的细胞类型后，一个单一的梯度步骤与有限数量的训练样本。我们表明，贝叶斯不确定性的主动学习可以进一步提高性能时，训练样本的数量是非常小的。仅使用1%的训练数据和一个更新步骤，我们在新的细胞类型分类任务上实现了90%的准确率，比最先进的元学习算法提高了50%。

Deep Neural Networks (or DNNs) must constantly cope with distribution changes in the input data when the task of interest or the data collection protocol changes. Retraining a network from scratch to combat this issue poses a significant cost. Meta-learning aims to deliver an adaptive model that is sensitive to these underlying distribution changes, but requires many tasks during the meta-training process. In this paper, we propose a tAsk-auGmented actIve meta-LEarning (AGILE) method to efficiently adapt DNNs to new tasks by using a small number of training examples. AGILE combines a meta-learning algorithm with a novel task augmentation technique which we use to generate an initial adaptive model. It then uses Bayesian dropout uncertainty estimates to actively select the most difficult samples when updating the model to a new task. This allows AGILE to learn with fewer tasks and a few informative samples, achieving high performance with a limited dataset. We perform our experiments using the brain cell classification task and compare the results to a plain meta-learning model trained from scratch. We show that the proposed task-augmented meta-learning framework can learn to classify new cell types after a single gradient step with a limited number of training samples. We show that active learning with Bayesian uncertainty can further improve the performance when the number of training samples is extremely small. Using only 1% of the training data and a single update step, we achieved 90% accuracy on the new cell type classification task, a 50% points improvement over a state-of-the-art meta-learning algorithm.

Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification

文献摘要

相似文献