Skip navigation
Please use this identifier to cite or link to this item: https://libeldoc.bsuir.by/handle/123456789/60622
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChen, Y. M.-
dc.coverage.spatialМинскen_US
dc.date.accessioned2025-06-30T08:31:14Z-
dc.date.available2025-06-30T08:31:14Z-
dc.date.issued2025-
dc.identifier.citationChen, Y. M. Methods of low data image classification with neural network / Y. M. Chen // Технологии передачи и обработки информации : материалы Международного научно-технического семинара, Минск, апрель 2025 г. / Белорусский государственный университет информатики и радиоэлектроники ; редкол.: В. Ю. Цветков [и др.]. – Минск, 2025. – С. 162–164.en_US
dc.identifier.urihttps://libeldoc.bsuir.by/handle/123456789/60622-
dc.description.abstractImage classification has evolved from relying on handcrafted feature engineering to a data-driven deep learning paradigm, with recent breakthroughs extending its capabilities to zeroshot and few-shot learning scenarios. This paper introduces emerging paradigms for low-data scenarios: zero-shot learning methods, including multimodal models (e.g., CLIP) that align visual and textual embeddings for open vocabulary classification and generative frameworks for synthesizing features of unseen classes; and (2) few-shot learning strategies, such as meta-learning (e.g., MAML), metric-based networks (e.g., ProtoNet), and fast adaptation techniques (e.g., Tip-Adapter) that leverage pre-trained knowledge for fast adaptation. While these methods reduce the reliance on labeled data, challenges remain in domain adaptation, fine-grained classification, and computational efficiency.en_US
dc.language.isoenen_US
dc.publisherБГУИРen_US
dc.subjectматериалы конференцийen_US
dc.subjectImage classificationen_US
dc.subjectDeep learningen_US
dc.subjectZero-shot learningen_US
dc.subjectFew-shot learningen_US
dc.subjectCLIPen_US
dc.subjectConvolutional Neural Networksen_US
dc.titleMethods of low data image classification with neural networken_US
dc.typeArticleen_US
Appears in Collections:Технологии передачи и обработки информации : материалы Международного научно-технического семинара (2025)

Files in This Item:
File Description SizeFormat 
Chen_Methods.pdf411.23 kBAdobe PDFView/Open
Show simple item record Google Scholar

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.