Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications.
Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications.
复制标题
DOI：
10.1109/tpami.2017.2656884
复制
发表时间：
2018-05
影响因子：
23.6
通讯作者：
Mao JH
中科院分区：
文献类型：
--
作者：
Chang H;Han J;Zhong C;Snijders AM;Mao JH
（I）跨领域学习可转移知识的能力;以及（II）针对具有相当小的数据规模的任务微调预先学习的基础知识的能力是非常重要的。许多现有的迁移学习技术都是有监督的方法，其中深度学习具有学习领域可迁移知识的能力，可以在大量标记数据上训练大规模网络。然而，在许多生物医学任务中，数据和相应的标签都非常有限，迫切需要无监督的迁移学习能力。在本文中，我们提出了一种新的多尺度卷积稀疏编码（MSCSC）方法，该方法（I）以联合方式自动学习不同尺度的滤波器组，并增强学习模式的尺度特异性;（II）提供了一种无监督的解决方案，用于学习可转移的基础知识并将其微调到目标任务。MSCSC的广泛的实验评估表明，建议MSCSC在定期和迁移学习任务在各个生物医学领域的有效性。
The capabilities of (I) learning transferable knowledge across domains; and (II) fine-tuning the pre-learned base knowledge towards tasks with considerably smaller data scale are extremely important. Many of the existing transfer learning techniques are supervised approaches, among which deep learning has the demonstrated power of learning domain transferrable knowledge with large scale network trained on massive amounts of labeled data. However, in many biomedical tasks, both the data and the corresponding label can be very limited, where the unsupervised transfer learning capability is urgently needed. In this paper, we proposed a novel multi-scale convolutional sparse coding (MSCSC) method, that (I) automatically learns filter banks at different scales in a joint fashion with enforced scale-specificity of learned patterns; and (II) provides an unsupervised solution for learning transferable base knowledge and fine-tuning it towards target tasks. Extensive experimental evaluation of MSCSC demonstrates the effectiveness of the proposed MSCSC in both regular and transfer learning tasks in various biomedical domains.