CATEGORY DISCOVERY AND IMAGE AUTO-ANNOTATION VIA LOOPED PSEUDO-TASK OPTIMIZATION

摘要

Methods and apparatus are disclosed for providing a looped deep pseudo-task automation approach for automatic category discovery as can be applied to a collection of images. In one example of the disclosed technology, a method of analyzing a collection of images includes extracting at least a portion of the activation values and weights associated with internal nodes of the neural network responsive to a respective input image of the collection of images being applied to the neural network, encoding the extracted activation values and weights, producing encoded vectors, clustering at least a portion of the collection of images based on similarities of the encoded vectors, to produce a plurality of clusters, and evaluating the clusters with a convergence criteria.