{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11308353","patent":{"patent_number":"US-11308353","title":"Classifying digital images in few-shot tasks based on neural networks trained using manifold mixup regularization and self-supervision","assignee":null,"inventors":[],"filing_date":"2019-10-23T00:00:00.000Z","publication_date":"2022-04-19T00:00:00.000Z","cpc_codes":["G06N","G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06V","G06V","G06V"],"num_claims":20,"abstract":"The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-supervision and manifold mixup. For example, the disclosed systems can train a feature extractor as part of a base neural network utilizing self-supervision and manifold mixup. Indeed, the disclosed systems can apply manifold mixup regularization over a feature manifold learned via self-supervised training such as rotation training or exemplar training. Based on training the feature extractor, the disclosed systems can also train a classifier to classify digital images into novel classes not present within the base classes used to train the feature extractor."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Classifying digital images in few-shot tasks based on neural networks trained using manifold mixup regularization and self-supervision","description":"The present disclosure relates to systems, methods, and non-transitory computer readable media for training a classification neural network to classify digital images in few-shot tasks based on self-s","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11308353","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-11308353","citation_suggestion":"Patentable. \"Classifying digital images in few-shot tasks based on neural networks trained using manifold mixup regularization and self-supervision\" (US-11308353). https://patentable.app/patents/US-11308353","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11308353","json":"https://patentable.app/api/llm-context/US-11308353","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T11:20:26.522Z"}