Unsupervised natural image patch learning

Dov Danon*, Hadar Averbuch-Elor, Ohad Fried, Daniel Cohen-Or

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


A metric for natural image patches is an important tool for analyzing images. An efficient means of learning one is to train a deep network to map an image patch to a vector space, in which the Euclidean distance reflects patch similarity. Previous attempts learned such an embedding in a supervised manner, requiring the availability of many annotated images. In this paper, we present an unsupervised embedding of natural image patches, avoiding the need for annotated images. The key idea is that the similarity of two patches can be learned from the prevalence of their spatial proximity in natural images. Clearly, relying on this simple principle, many spatially nearby pairs are outliers. However, as we show, these outliers do not harm the convergence of the metric learning. We show that our unsupervised embedding approach is more effective than a supervised one or one that uses deep patch representations. Moreover, we show that it naturally lends itself to an efficient self-supervised domain adaptation technique onto a target domain that contains a common foreground object.

Original languageEnglish
Pages (from-to)229-237
Number of pages9
JournalComputational Visual Media
Issue number3
StatePublished - 1 Sep 2019


  • metric learning
  • unsupervised learning


Dive into the research topics of 'Unsupervised natural image patch learning'. Together they form a unique fingerprint.

Cite this