Zero-Shot Image Recognition via Learning Dual Prototype Accordance Across Meta-Domains

Zero-Shot Image Recognition via Learning Dual Prototype Accordance Across Meta-Domains

Zero-shot learning (ZSL) aims to recognize unseen classes by transferring semantic knowledge from seen categories. However, existing methods often struggle with the persistent semantic gap caused by limited semantic descriptors and rigid visual feature modeling. In particular, modeling pre-defined c...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 34(2025) vom: 15., Seite 6361-6373
Auteur principal: Ren, Bocheng (Auteur)
Autres auteurs: Yi, Yuanyuan, Zhang, Qingchen, Liu, Debin
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM392639858
003 DE-627
005 20251008232028.0
007 cr uuu---uuuuu
008 250917s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2025.3607588  |2 doi 
028 5 2 |a pubmed25n1593.xml 
035 |a (DE-627)NLM392639858 
035 |a (NLM)40953417 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Ren, Bocheng  |e verfasserin  |4 aut 
245 1 0 |a Zero-Shot Image Recognition via Learning Dual Prototype Accordance Across Meta-Domains 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 08.10.2025 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Zero-shot learning (ZSL) aims to recognize unseen classes by transferring semantic knowledge from seen categories. However, existing methods often struggle with the persistent semantic gap caused by limited semantic descriptors and rigid visual feature modeling. In particular, modeling pre-defined class-level attribute descriptions as ground truth hinders effective semantic-to-visual alignment to some extent. To mitigate these issues, we propose the Bilateral-guided Prototype Refinement Network (BPRN), a novel ZSL framework designed to refine dual prototypes across meta-domains of varying scales. Specifically, we first disentangle the relationships among class-level semantics and use them to generate corresponding pseudo-visual prototypes. Then, by leveraging distribution information across dual prototypes in different meta-domains, BPRN achieves bidirectional calibration between visual-to-semantic and semantic-to-visual modalities. Finally, a synthesized class-level representation derived from the refined dual prototypes is employed for inference, instead of relying on a single prototype. Extensive experiments conducted on five widely-used ZSL benchmark datasets demonstrate that BPRN consistently achieves competitive or even superior performance. Specifically, in the GZSL scenario, BPRN shows improvements of 2.1%, 7.3%, 6.1%, and 4.8% on AWA1, AWA2, SUN, and aPY, respectively, compared to existing embedding-based ZSL methods. Ablation studies and visualization analyses further validate the effectiveness of the proposed components 
650 4 |a Journal Article 
700 1 |a Yi, Yuanyuan  |e verfasserin  |4 aut 
700 1 |a Zhang, Qingchen  |e verfasserin  |4 aut 
700 1 |a Liu, Debin  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 34(2025) vom: 15., Seite 6361-6373  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:34  |g year:2025  |g day:15  |g pages:6361-6373 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2025.3607588  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 34  |j 2025  |b 15  |h 6361-6373