Abstract: Systems, apparatuses, and methods for efficiently and accurately processing an image in order to detect and identify one or more objects contained in the image, and methods that may be implemented on mobile or other resource constrained devices. Embodiments of the invention introduce simple, efficient, and accurate approximations to the functions performed by a convolutional neural network (CNN); this is achieved by binarization (i.e., converting one form of data to binary values) of the weights and of the intermediate representations of data in a convolutional neural network. The inventive binarization methods include optimization processes that determine the best approximations of the convolution operations that are part of implementing a CNN using binary operations.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for creating visualizations to explain the outputs produced by models designed for object detection. To accomplish this, a graphics editing platform can obtain a reference output that identifies a region of pixels in a digital image that allegedly contains an object. Then, the graphics editing platform can compute the similarity between the reference output and a series of outputs generated by a model upon being applied to masked versions of the digital image. A visualization component can be produced based on the similarity.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for creating visualizations to explain the outputs produced by models designed for object detection. To accomplish this, a graphics editing platform can obtain a reference output that identifies a region of pixels in a digital image that allegedly contains an object. Then, the graphics editing platform can compute the similarity between the reference output and a series of outputs generated by a model upon being applied to masked versions of the digital image. A visualization component can be produced based on the similarity.

Abstract: A computer-implemented technique can receive, at a computing device including one or more processors, a plurality of photos. The technique can extract quality features and similarity features for each of the plurality of photos and can obtain weights for the various quality features and similarity features based on an analysis of a reference photo collection. The technique can generate a quality metric for each of the plurality of photos and can generate a similarity matrix for the plurality of photos by analyzing the various quality features and similarity features and using the obtained weights. The technique can perform joint global maximization of photo quality and photo diversity using the quality metrics and the similarity matrix in order to select a subset of the plurality of photos having a high degree of representativeness. The technique can then store the subset of the plurality of photos in a memory.