|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM326548971 |
| 003 |
DE-627 |
| 005 |
20231225194832.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2021.3087709
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1088.xml
|
| 035 |
|
|
|a (DE-627)NLM326548971
|
| 035 |
|
|
|a (NLM)34106845
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Deng, Jiankang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a ArcFace
|b Additive Angular Margin Loss for Deep Face Recognition
|
| 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 Completed 16.09.2022
|
| 500 |
|
|
|a Date Revised 19.11.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability. In this paper, we first introduce an Additive Angular Margin Loss (ArcFace), which not only has a clear geometric interpretation but also significantly enhances the discriminative power. Since ArcFace is susceptible to the massive label noise, we further propose sub-center ArcFace, in which each class contains K sub-centers and training samples only need to be close to any of the K positive sub-centers. Sub-center ArcFace encourages one dominant sub-class that contains the majority of clean faces and non-dominant sub-classes that include hard or noisy faces. Based on this self-propelled isolation, we boost the performance through automatically purifying raw web faces under massive real-world noise. Besides discriminative feature embedding, we also explore the inverse problem, mapping feature vectors to face images. Without training any additional generator or discriminator, the pre-trained ArcFace model can generate identity-preserved face images for both subjects inside and outside the training data only by using the network gradient and Batch Normalization (BN) priors. Extensive experiments demonstrate that ArcFace can enhance the discriminative feature embedding as well as strengthen the generative face synthesis
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Guo, Jia
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Jing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xue, Niannan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Kotsia, Irene
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Zafeiriou, Stefanos
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 44(2022), 10 vom: 09. Okt., Seite 5962-5979
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:44
|g year:2022
|g number:10
|g day:09
|g month:10
|g pages:5962-5979
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2021.3087709
|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 44
|j 2022
|e 10
|b 09
|c 10
|h 5962-5979
|