arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1509.05463cs.CVcs.AI
收藏

使用堆叠多通道自编码器从合成数据学习

Learning from Synthetic Data Using a Stacked Multichannel Autoencoder

Illinois Institute of Technology(伊利诺伊理工学院);Disney Research(迪士尼研究院)

Xi Zhang, Yanwei Fu, Shanshan Jiang, Leonid Sigal, Gady Agam

摘要:

从合成数据中学习具有许多重要和实际的应用。应用的一个例子是照片草图识别。使用合成数据是具有挑战性的,由于合成数据和真实数据之间的特征分布的差异,我们称之为合成差距的现象。在本文中,我们研究和形式化的一个通用框架堆叠多通道自动编码器(SMCAE),使弥合合成的差距,并从合成数据更有效地学习。特别是,我们表明,我们的SMCAE不仅可以转换和使用合成数据上具有挑战性的人脸素描识别任务,但它也可以帮助模拟真实图像,可用于训练分类识别。初步实验验证了该框架的有效性。

英文摘要:

Learning from synthetic data has many important and practical applications. An example of application is photo-sketch recognition. Using synthetic data is challenging due to the differences in feature distributions between synthetic and real data, a phenomenon we term synthetic gap. In this paper, we investigate and formalize a general framework-Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently. In particular, we show that our SMCAE can not only transform and use synthetic data on the challenging face-sketch recognition task, but that it can also help simulate real images, which can be used for training classifiers for recognition. Preliminary experiments validate the effectiveness of the framework.

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。

↑