صورة الغلاف

Enhancing Zero-Shot Learning Through Kernelized Visual Prototypes and Similarity Learning

محفوظ في:
الحاوية / القاعدة:Mathematics vol. 13, no. 3 (2025), p. 412
المؤلف الرئيسي: Cheng, Kanglong
مؤلفون آخرون: Bowen, Fang
منشور في:
MDPI AG
الموضوعات:
Similarity
Visual discrimination
Research methodology
Teaching methods
Zero-shot learning
Classification
Maps
Prototypes
Image classification
Image acquisition
Similarity measures
Distance learning
Semantics
الوصول للمادة أونلاين:Citation/Abstract
Full Text + Graphics
Full Text - PDF
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
مستخلص:Zero-shot learning (ZSL) holds significant promise for scaling image classification to previously unseen classes by leveraging previously acquired knowledge. However, conventional ZSL methods face challenges such as domain-shift and hubness problems. To address these issues, we propose a novel kernelized similarity learning approach that reduces intraclass similarity while increasing interclass similarity. Specifically, we utilize kernelized ridge regression to learn visual prototypes for unseen classes in the semantic vectors. Furthermore, we introduce kernel polarization and autoencoder structures into the similarity function to enhance discriminative ability and mitigate the hubness and domain-shift problems. Extensive experiments on five benchmark datasets demonstrate that our method outperforms state-of-the-art ZSL and generalized zero-shot learning (GZSL) methods, highlighting its effectiveness in improving classification performance for unseen classes.
تدمد:2227-7390
DOI:10.3390/math13030412
المصدر:Engineering Database