{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11263753","patent":{"patent_number":"US-11263753","title":"Method for training a convolutional neural network for image recognition using image-conditioned masked language modeling","assignee":null,"inventors":[],"filing_date":"2020-04-07T00:00:00.000Z","publication_date":"2022-03-01T00:00:00.000Z","cpc_codes":["G06N","G06T","G06N","G06N","G06T","G06T","G06T"],"num_claims":6,"abstract":"A method and system pre-trains a convolutional neural network for image recognition based upon masked language modeling by inputting, to the convolutional neural network, an image; outputting, from the convolutional neural network, a visual embedding tensor of visual embedding vectors; tokenizing a caption to create a list of tokens, at least one token having visual correspondence to the image received by the convolutional neural network; randomly selecting one of the tokens in the list of tokens to be masked, the selected token being taken as ground truth; computing, using a language model neural network, hidden representations of the tokens; using the hidden representation of the masked token, as a query vector, to pool the visual embedding vectors in the visual embedding tensor, attentively; predicting the masked token by mapping the pooled visual embedding vectors to the tokens; determining a prediction loss associated with the masked token; and back-propagating the prediction loss to the convolutional neural network to tune parameters thereof."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Method for training a convolutional neural network for image recognition using image-conditioned masked language modeling","description":"A method and system pre-trains a convolutional neural network for image recognition based upon masked language modeling by inputting, to the convolutional neural network, an image; outputting, from th","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11263753","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11263753","citation_suggestion":"Patentable. \"Method for training a convolutional neural network for image recognition using image-conditioned masked language modeling\" (US-11263753). https://patentable.app/patents/US-11263753","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11263753","json":"https://patentable.app/api/llm-context/US-11263753","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T23:03:03.320Z"}