|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM349677158 |
| 003 |
DE-627 |
| 005 |
20250304044143.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3225788
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1165.xml
|
| 035 |
|
|
|a (DE-627)NLM349677158
|
| 035 |
|
|
|a (NLM)36455092
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Xu, Yinghao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a GH-Feat
|b Learning Versatile Generative Hierarchical Features From GANs
|
| 264 |
|
1 |
|c 2023
|
| 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 Completed 07.05.2023
|
| 500 |
|
|
|a Date Revised 07.05.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Recent years witness the tremendous success of generative adversarial networks (GANs) in synthesizing photo-realistic images. GAN generator learns to compose realistic images and reproduce the real data distribution. Through that, a hierarchical visual feature with multi-level semantics spontaneously emerges. In this work we investigate that such a generative feature learned from image synthesis exhibits great potentials in solving a wide range of computer vision tasks, including both generative ones and more importantly discriminative ones. We first train an encoder by considering the pre-trained StyleGAN generator as a learned loss function. The visual features produced by our encoder, termed as Generative Hierarchical Features (GH-Feat), highly align with the layer-wise GAN representations, and hence describe the input image adequately from the reconstruction perspective. Extensive experiments support the versatile transferability of GH-Feat across a range of applications, such as image editing, image processing, image harmonization, face verification, landmark detection, layout prediction, image retrieval, etc. We further show that, through a proper spatial expansion, our developed GH-Feat can also facilitate fine-grained semantic segmentation using only a few annotations. Both qualitative and quantitative results demonstrate the appealing performance of GH-Feat. Code and models are available at https://genforce.github.io/ghfeat/
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Shen, Yujun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhu, Jiapeng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Ceyuan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zhou, Bolei
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 6 vom: 01. Juni, Seite 7395-7411
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnas
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:6
|g day:01
|g month:06
|g pages:7395-7411
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3225788
|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 45
|j 2023
|e 6
|b 01
|c 06
|h 7395-7411
|