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 1610.00243cs.LGcs.AIstat.ML
收藏

通过空间对比的深度无监督学习

Deep unsupervised learning through spatial contrasting

Technion - Israel Institute of Technology(以色列理工学院)

Elad Hoffer, Itay Hubara, Nir Ailon

摘要:

在过去的几年里,卷积网络已经成为各种视觉任务中表现最好的模型。然而,它们最适合从大量标记数据中进行监督学习。以前的尝试已经通过应用无监督技术来使用未标记的数据来提高模型性能。这些尝试需要不同的架构和培训方法。在这项工作中,我们提出了一种新的方法,用于卷积网络的无监督训练,该方法基于图像内空间区域之间的对比。该标准可以在传统的神经网络中使用,并使用标准技术(如SGD和反向传播)进行训练,从而补充监督方法。

英文摘要:

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have been made to use unlabeled data to improve model performance by applying unsupervised techniques. These attempts require different architectures and training methods. In this work we present a novel approach for unsupervised training of Convolutional networks that is based on contrasting between spatial regions within images. This criterion can be employed within conventional neural networks and trained using standard techniques such as SGD and back-propagation, thus complementing supervised methods.

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。

↑