Instead of distilling a model end-to-end, we propose to split it into smaller sub-networks - also called neighbourhoods - that are then trained independently.
The sky is a major component of the appearance of a photograph, and its color and tone can strongly influence the mood of a picture.
Shallow depth-of-field is commonly used by photographers to isolate a subject from a distracting background.
Traditionally, for this problem supervision is expressed in the form of sets of points that follow an ordinal relationship -- an anchor point $x$ is similar to a set of positive points $Y$, and dissimilar to a set of negative points $Z$, and a loss defined over these distances is minimized.
Data seems cheap to get, and in many ways it is, but the process of creating a high quality labeled dataset from a mass of data is time-consuming and expensive.
Modern search engines receive large numbers of business related, local aware queries.