{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11960570","patent":{"patent_number":"US-11960570","title":"Learning contrastive representation for semantic correspondence","assignee":null,"inventors":[],"filing_date":"2021-08-25T00:00:00.000Z","publication_date":"2024-04-16T00:00:00.000Z","cpc_codes":["G06F","G06V","G06F","G06N","G06N","G06N","G06N","G06N","G06V","G06V","G06V","G06V","G06V","G06V"],"num_claims":20,"abstract":"A multi-level contrastive training strategy for training a neural network relies on image pairs (no other labels) to learn semantic correspondences at the image level and region or pixel level. The neural network is trained using contrasting image pairs including different objects and corresponding image pairs including different views of the same object. Conceptually, contrastive training pulls corresponding image pairs closer and pushes contrasting image pairs apart. An image-level contrastive loss is computed from the outputs (predictions) of the neural network and used to update parameters (weights) of the neural network via backpropagation. The neural network is also trained via pixel-level contrastive learning using only image pairs. Pixel-level contrastive learning receives an image pair, where each image includes an object in a particular category."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Learning contrastive representation for semantic correspondence","description":"A multi-level contrastive training strategy for training a neural network relies on image pairs (no other labels) to learn semantic correspondences at the image level and region or pixel level. The ne","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11960570","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-11960570","citation_suggestion":"Patentable. \"Learning contrastive representation for semantic correspondence\" (US-11960570). https://patentable.app/patents/US-11960570","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11960570","json":"https://patentable.app/api/llm-context/US-11960570","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T02:41:02.046Z"}