.png){kind=icon}
Return
Unsupervised natural image patch learning
.png){kind=icon}
OA
AI
DOI：10.1007/s41095-019-0147-y.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
unsupervised learning
metric learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
18.3
Papers:
319
Citations:
2.6K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSave
ShareSaveShareSave no more
no more