arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1206.4609cs.CVcs.LGstat.ML
收藏

关于多视图特征学习

On multi-view feature learning

University of Frankfurt(法兰克福大学)

Roland Memisevic

摘要:

稀疏编码是学习局部特征用于物体识别的常用方法。最近,人们对从时空、双目或其他多观测数据中学习特征越来越感兴趣,其中目标是对图像之间的关系而不是单个图像的内容进行编码。我们提供了一个多视图特征学习的分析,它表明隐变量通过检测多个图像扭曲之间共享的特征空间中的旋转角度来编码变换。我们的分析有助于解释最近的实验结果,这些结果表明,在视频上训练复杂的细胞模型时,会出现特定于转化的特征。我们的分析还表明,变换不变特征可以作为学习变换表示的副产品出现。

英文摘要:

Sparse coding is a common approach to learning local features for object recognition. Recently, there has been an increasing interest in learning features from spatio-temporal, binocular, or other multi-observation data, where the goal is to encode the relationship between images rather than the content of a single image. We provide an analysis of multi-view feature learning, which shows that hidden variables encode transformations by detecting rotation angles in the eigenspaces shared among multiple image warps. Our analysis helps explain recent experimental results showing that transformation-specific features emerge when training complex cell models on videos. Our analysis also shows that transformation-invariant features can emerge as a by-product of learning representations of transformations.

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。

↑