Prototype-Augmented Self-Supervised Generative Network for Generalized Zero-Shot Learning
Generalized Zero-Shot Learning (GZSL) aims at recognizing images from both seen and unseen classes by constructing correspondences between visual images and semantic embedding. However, existing methods suffer from a strong bias problem, where unseen images in the target domain tend to be recognized as seen classes in the source domain. To address this issue, we propose a Prototype-augmented Self-supervised Generative Network by integrating self-supervised learning and prototype learning into a feature generating model for GZSL. The proposed model enjoys several advantages. First, we propose a Self-supervised Learning Module to exploit inter-domain relationships, where we introduce anchors as a bridge between seen and unseen categories. In the shared space, we pull the distribution of the target domain away from the source domain and obtain domain-aware features. To our best knowledge, this is the first work to introduce self-supervised learning into GZSL as learning guidance. Second, a Prototype Enhancing Module is proposed to utilize class prototypes to model reliable target domain distribution in finer granularity. In this module, a Prototype Alignment mechanism and a Prototype Dispersion mechanism are combined to guide the generation of better target class features with intra-class compactness and inter-class separability. Extensive experimental results on five standard benchmarks demonstrate that our model performs favorably against state-of-the-art GZSL methods.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:33 |
|---|---|
| Enthalten in: |
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society - 33(2024) vom: 15., Seite 1938-1951 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wu, Jiamin [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 18.03.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1109/TIP.2024.3351439 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM367150719 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM367150719 | ||
| 003 | DE-627 | ||
| 005 | 20240319232456.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240116s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TIP.2024.3351439 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1336.xml |
| 035 | |a (DE-627)NLM367150719 | ||
| 035 | |a (NLM)38224517 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wu, Jiamin |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Prototype-Augmented Self-Supervised Generative Network for Generalized Zero-Shot Learning |
| 264 | 1 | |c 2024 | |
| 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 18.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Generalized Zero-Shot Learning (GZSL) aims at recognizing images from both seen and unseen classes by constructing correspondences between visual images and semantic embedding. However, existing methods suffer from a strong bias problem, where unseen images in the target domain tend to be recognized as seen classes in the source domain. To address this issue, we propose a Prototype-augmented Self-supervised Generative Network by integrating self-supervised learning and prototype learning into a feature generating model for GZSL. The proposed model enjoys several advantages. First, we propose a Self-supervised Learning Module to exploit inter-domain relationships, where we introduce anchors as a bridge between seen and unseen categories. In the shared space, we pull the distribution of the target domain away from the source domain and obtain domain-aware features. To our best knowledge, this is the first work to introduce self-supervised learning into GZSL as learning guidance. Second, a Prototype Enhancing Module is proposed to utilize class prototypes to model reliable target domain distribution in finer granularity. In this module, a Prototype Alignment mechanism and a Prototype Dispersion mechanism are combined to guide the generation of better target class features with intra-class compactness and inter-class separability. Extensive experimental results on five standard benchmarks demonstrate that our model performs favorably against state-of-the-art GZSL methods | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Zhang, Tianzhu |e verfasserin |4 aut | |
| 700 | 1 | |a Zha, Zheng-Jun |e verfasserin |4 aut | |
| 700 | 1 | |a Luo, Jiebo |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Yongdong |e verfasserin |4 aut | |
| 700 | 1 | |a Wu, Feng |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 33(2024) vom: 15., Seite 1938-1951 |w (DE-627)NLM09821456X |x 1941-0042 |7 nnns |
| 773 | 1 | 8 | |g volume:33 |g year:2024 |g day:15 |g pages:1938-1951 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TIP.2024.3351439 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 33 |j 2024 |b 15 |h 1938-1951 | ||