arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.11829cs.LGstat.ML
收藏

通过潜在规范化的表示学习

Representation Learning Through Latent Canonicalizations

Stanford University(斯坦福大学);Facebook AI Research(脸书人工智能研究院);Georgia Tech(佐治亚理工学院)

Or Litany, Ari Morcos, Srinath Sridhar, Leonidas Guibas, Judy Hoffman

摘要:

我们寻求学习一个大型注释数据源,推广到一个目标域使用有限的新的监督表示。这个问题的许多先前的方法都集中在学习“解纠缠”表示,使得当个体因素在新的域中变化时,仅需要更新表示的一部分。在这项工作中,我们寻求解纠缠表示的泛化能力,但放松了显式潜在解纠缠的要求,而是通过要求它们可由学习的线性变换操纵来鼓励个体变异因子的线性。我们称这些转换为潜在的规范化器,因为它们旨在将因子的值修改为预定的(但任意的)规范值(例如,使图像前景为黑色)。假设一个源域可以访问指定图像内变化因素的元标签,我们通过实验证明,我们的方法有助于减少与一些监督基线相比,推广到类似目标域所需的观测数量。

英文摘要:

We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision. Many prior approaches to this problem have focused on learning "disentangled" representations so that as individual factors vary in a new domain, only a portion of the representation need be updated. In this work, we seek the generalization power of disentangled representations, but relax the requirement of explicit latent disentanglement and instead encourage linearity of individual factors of variation by requiring them to be manipulable by learned linear transformations. We dub these transformations latent canonicalizers, as they aim to modify the value of a factor to a pre-determined (but arbitrary) canonical value (e.g., recoloring the image foreground to black). Assuming a source domain with access to meta-labels specifying the factors of variation within an image, we demonstrate experimentally that our method helps reduce the number of observations needed to generalize to a similar target domain when compared to a number of supervised baselines.

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。

↑