St. Petersburg Plants

CODE: GitHub
DATATYPE: images
SOURCE: Instagram
PLACE: St. Petersburg
YEARS: 2014-2015
SIZE: 1254
SUBSET: "plant"
VIZTYPE: map
FEATURES: tag space
FEAT SRC: Google Cloud Vision
ORIG FEAT DIMS: 697
EMBEDDING: t-SNE
BINS: 60
GRIDDING: fill
CRITERION: adjacency
ANNOTATIONS: tag lists
% ANN: 55

This is a "map" visualization, meaning that the images are plotted in a coordinate space — here, a 2D t-SNE embedding of a 697-dimensional tag space generated by Google's Cloud Vision API. Since Google's classifiers use sophisticated measures of visual similarity, its outputs produce a sophisticated visual similarity space. The images are gridded into 60 bins in this space, with some images allowed to plot adjacently to their true locations in order to increase the plotting volume. The map is also partially annotated with short tag lists. Yellow markers point to the annotated images.