|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM295548991 |
| 003 |
DE-627 |
| 005 |
20250225035139.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2020 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2019.2907634
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n0985.xml
|
| 035 |
|
|
|a (DE-627)NLM295548991
|
| 035 |
|
|
|a (NLM)30932829
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Tang, Zhiqiang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Towards Efficient U-Nets
|b A Coupled and Quantized Approach
|
| 264 |
|
1 |
|c 2020
|
| 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 12.02.2021
|
| 500 |
|
|
|a Date Revised 12.02.2021
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a In this paper, we propose to couple stacked U-Nets for efficient visual landmark localization. The key idea is to globally reuse features of the same semantic meanings across the stacked U-Nets. The feature reuse makes each U-Net light-weighted. Specially, we propose an order- K coupling design to trim off long-distance shortcuts, together with an iterative refinement and memory sharing mechanism. To further improve the efficiency, we quantize the parameters, intermediate features, and gradients of the coupled U-Nets to low bit-width numbers. We validate our approach in two tasks: human pose estimation and facial landmark localization. The results show that our approach achieves state-of-the-art localization accuracy but using ∼ 70% fewer parameters, ∼ 30% less inference time, ∼ 98% less model size, and saving ∼ 75% training memory compared with benchmark localizers
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, U.S. Gov't, Non-P.H.S.
|
| 700 |
1 |
|
|a Peng, Xi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Kang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Metaxas, Dimitris N
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 42(2020), 8 vom: 01. Aug., Seite 2038-2050
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:42
|g year:2020
|g number:8
|g day:01
|g month:08
|g pages:2038-2050
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2019.2907634
|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 42
|j 2020
|e 8
|b 01
|c 08
|h 2038-2050
|