Identifying digital attributes from multiple attribute groups within target digital images utilizing a deep cognitive attribution neural network

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computer system to:

• identify a query comprising a digital image portraying an object comprising a plurality of attributes of a plurality of attribute groups;
• utilize a base localization neural network of a cognitive attribution neural network to generate one or more localization feature vectors based on the digital image;
• generate, based on the one or more localization feature vectors, a plurality of localization feature embeddings for the plurality of attribute groups;
• determine, utilizing a plurality of attribute group classifiers of the cognitive attribution neural network, a set of attributes for the plurality of attribute groups based on the plurality of localization feature embeddings, each attribute group classifier of the plurality of attribute group classifiers configured to generate a subset of attributes corresponding to an attribute group of the plurality of attribute groups;
• and
• generate tags for the object portrayed in the digital image based on the set of attributes.

A system comprising:

• one or more memory devices comprising:
• a digital image portraying an object;
• and
• a cognitive attribution neural network comprising a base localization neural network and a plurality of attribute group classifiers, wherein the base localization neural network comprises a plurality of alternating dilated convolution layers and inception layers;
• and
• one or more server devices that cause the system to:
• generate one or more localization feature vectors by analyzing the digital image via the plurality of alternating dilated convolution layers and inception layers of the base localization neural network of the cognitive attribution neural network;
• generate a plurality of attribute localization feature embeddings for a plurality of attribute groups based on the one or more localization feature vectors;
• determine, utilizing each attribute group classifier of the plurality of attribute group classifiers, a subset of attributes corresponding to an attribute group of the plurality of attribute groups, wherein:
• a first attribute group classifier of the cognitive attribution neural network determines, based on a first attribute localization feature embedding, a first attribute for a first attribute group;
• and
• a second attribute group classifier of the cognitive attribution neural network determines, based on a second attribute localization feature embedding, a second attribute for a second attribute group;
• and
• generate, for the object portrayed in the digital image, a first tag based on the first attribute for the first attribute group and a second tag based on the second attribute for the second attribute group.