Enhancing Zero-Shot Learning Through Kernelized Visual Prototypes and Similarity Learning
I tiakina i:
| I whakaputaina i: | Mathematics vol. 13, no. 3 (2025), p. 412 |
|---|---|
| Kaituhi matua: | |
| Ētahi atu kaituhi: | |
| I whakaputaina: |
MDPI AG
|
| Ngā marau: | |
| Urunga tuihono: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Ngā Tūtohu: |
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3165832771 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2227-7390 | ||
| 024 | 7 | |a 10.3390/math13030412 |2 doi | |
| 035 | |a 3165832771 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231533 |2 nlm | ||
| 100 | 1 | |a Cheng, Kanglong | |
| 245 | 1 | |a Enhancing Zero-Shot Learning Through Kernelized Visual Prototypes and Similarity Learning | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a 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. | |
| 653 | |a Similarity | ||
| 653 | |a Visual discrimination | ||
| 653 | |a Research methodology | ||
| 653 | |a Teaching methods | ||
| 653 | |a Zero-shot learning | ||
| 653 | |a Classification | ||
| 653 | |a Maps | ||
| 653 | |a Prototypes | ||
| 653 | |a Image classification | ||
| 653 | |a Image acquisition | ||
| 653 | |a Similarity measures | ||
| 653 | |a Distance learning | ||
| 653 | |a Semantics | ||
| 700 | 1 | |a Bowen, Fang | |
| 773 | 0 | |t Mathematics |g vol. 13, no. 3 (2025), p. 412 | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3165832771/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3165832771/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3165832771/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |