arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.03534stat.MLcs.LG
收藏

无监督Transductive Domain Adaptation

Unsupervised Transductive Domain Adaptation

Stanford University(斯坦福大学);Cornell University(康奈尔大学);Brain of Things

Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese

摘要:

大规模标记数据集和深层模型的监督学习在学习和识别的不同领域实现了范式转变。然而,这种方法在训练和测试数据分布之间存在域转移的情况下仍然存在泛化问题。在这方面,已经提出了无监督域自适应算法来直接解决域移位问题。在本文中,我们从转换的角度来探讨这个问题。我们将域转移和转导目标推理到我们的框架,通过联合解决一个不对称的相似性度量和最佳的转导目标标签分配。我们还表明,我们的模型可以很容易地扩展到深度特征学习,以学习在目标域中具有区分性的特征。我们的实验表明,该方法显着优于国家的最先进的算法在对象识别和数字分类实验的大幅度提高。

英文摘要:

Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain shift between the training and the test data distribution. In this regard, unsupervised domain adaptation algorithms have been proposed to directly address the domain shift problem. In this paper, we approach the problem from a transductive perspective. We incorporate the domain shift and the transductive target inference into our framework by jointly solving for an asymmetric similarity metric and the optimal transductive target label assignment. We also show that our model can easily be extended for deep feature learning in order to learn features which are discriminative in the target domain. Our experiments show that the proposed method significantly outperforms state-of-the-art algorithms in both object recognition and digit classification experiments by a large margin.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑