|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM328551007 |
| 003 |
DE-627 |
| 005 |
20231225203155.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2021.3097169
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1095.xml
|
| 035 |
|
|
|a (DE-627)NLM328551007
|
| 035 |
|
|
|a (NLM)34310301
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Liang, Zhiyuan
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Person Foreground Segmentation by Learning Multi-Domain Networks
|
| 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 24.12.2021
|
| 500 |
|
|
|a Date Revised 24.12.2021
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status MEDLINE
|
| 520 |
|
|
|a Separating the dominant person from the complex background is significant to the human-related research and photo-editing based applications. Existing segmentation algorithms are either too general to separate the person region accurately, or not capable of achieving real-time speed. In this paper, we introduce the multi-domain learning framework into a novel baseline model to construct the Multi-domain TriSeNet Networks for the real-time single person image segmentation. We first divide training data into different subdomains based on the characteristics of single person images, then apply a multi-branch Feature Fusion Module (FFM) to decouple the networks into the domain-independent and the domain-specific layers. To further enhance the accuracy, a self-supervised learning strategy is proposed to dig out domain relations during training. It helps transfer domain-specific knowledge by improving predictive consistency among different FFM branches. Moreover, we create a large-scale single person image segmentation dataset named MSSP20k, which consists of 22,100 pixel-level annotated images in the real world. The MSSP20k dataset is more complex and challenging than existing public ones in terms of scalability and variety. Experiments show that our Multi-domain TriSeNet outperforms state-of-the-art approaches on both public and the newly built datasets with real-time speed
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Guo, Kan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Xiaobo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Jin, Xiaogang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Shen, Jianbing
|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: 26., Seite 585-597
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:26
|g pages:585-597
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2021.3097169
|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 26
|h 585-597
|