|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM334648424 |
| 003 |
DE-627 |
| 005 |
20250302194041.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2021.3135480
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1115.xml
|
| 035 |
|
|
|a (DE-627)NLM334648424
|
| 035 |
|
|
|a (NLM)34928799
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Shermin, Tasfia
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning
|
| 264 |
|
1 |
|c 2022
|
| 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 29.12.2021
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen classes and preserving the distinction between seen-unseen classes is crucial for GZSL methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining seen-unseen classes distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the concept of the coupled generative adversarial network into a bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining distinctive information of seen-unseen classes in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Teng, Shyh Wei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sohel, Ferdous
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Murshed, Manzur
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lu, Guojun
|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 31(2022) vom: 20., Seite 721-733
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:20
|g pages:721-733
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2021.3135480
|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 31
|j 2022
|b 20
|h 721-733
|