Supervised Transfer Sparse Coding
Supervised Transfer Sparse Coding
复制标题
DOI：
10.1609/aaai.v28i1.8981
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Maruan Al-Shedivat;Jim Jing-Yan Wang;Majed Alzahrani;Jianhua Z. Huang;Xin Gao
中科院分区：
文献类型：
--
作者：
Maruan Al-Shedivat;Jim Jing-Yan Wang;Majed Alzahrani;Jianhua Z. Huang;Xin Gao
稀疏编码和转移学习技术的结合被证明在分类任务中是准确和稳健的，其中训练和测试对象具有共同的特征空间，但样本来自不同的底层分布，即属于不同的领域。在这种情况下的关键假设是，尽管领域差异，来自不同领域的样本共享一些共同的隐藏因素。以前的方法通常假设目标域中的所有对象都是未标记的，因此训练集只包括源域中的对象。然而，在现实世界的应用中，目标域通常有一些标记的对象，或者人们总是可以手动标记其中的一小部分。在本文中，我们探索了这种可能性，并展示了目标域中的少量标记数据如何显著地利用最先进的转移稀疏编码方法的分类精度。在此基础上，提出了一个同时优化稀疏表示、域转移和分类的统一框架--监督转移稀疏编码(STSC)。在三个应用上的实验结果表明，少量的人工标注，然后以有监督的方式学习模型，可以显着提高分类精度。
A combination of the sparse coding and transfer learning techniques was shown to be accurate and robust in classification tasks where training and testing objects have a shared feature space but are sampled from different underlying distributions, i.e., belong to different domains. The key assumption in such case is that in spite of the domain disparity, samples from different domains share some common hidden factors. Previous methods often assumed that all the objects in the target domain are unlabeled, and thus the training set solely comprised objects from the source domain. However, in real world applications, the target domain often has some labeled objects, or one can always manually label a small number of them. In this paper, we explore such possibility and show how a small number of labeled data in the target domain can significantly leverage classification accuracy of the state-of-the-art transfer sparse coding methods. We further propose a unified framework named supervised transfer sparse coding (STSC) which simultaneously optimizes sparse representation, domain transfer and classification. Experimental results on three applications demonstrate that a little manual labeling and then learning the model in a supervised fashion can significantly improve classification accuracy.