|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM26825298X |
| 003 |
DE-627 |
| 005 |
20231224222318.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2017 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2016.2552172
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n0894.xml
|
| 035 |
|
|
|a (DE-627)NLM26825298X
|
| 035 |
|
|
|a (NLM)28113885
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhiwu Lu
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Learning from Weak and Noisy Labels for Semantic Segmentation
|
| 264 |
|
1 |
|c 2017
|
| 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 20.09.2018
|
| 500 |
|
|
|a Date Revised 20.09.2018
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the tedious pixel-level annotation process, it can exploit the unlimited supply of user-tagged images from media-sharing sites such as Flickr for large scale applications. However, these `free' tags/labels are often noisy and few existing works address the problem of learning with both weak and noisy labels. In this work, we cast the WSSS problem into a label noise reduction problem. Specifically, after segmenting each image into a set of superpixels, the weak and potentially noisy image-level labels are propagated to the superpixel level resulting in highly noisy labels; the key to semantic segmentation is thus to identify and correct the superpixel noisy labels. To this end, a novel L1-optimisation based sparse learning model is formulated to directly and explicitly detect noisy labels. To solve the L1-optimisation problem, we further develop an efficient learning algorithm by introducing an intermediate labelling variable. Extensive experiments on three benchmark datasets show that our method yields state-of-the-art results given noise-free labels, whilst significantly outperforming the existing methods when the weak labels are also noisy
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Research Support, Non-U.S. Gov't
|
| 700 |
1 |
|
|a Zhenyong Fu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tao Xiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Peng Han
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liwei Wang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xin Gao
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 39(2017), 3 vom: 15. März, Seite 486-500
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:39
|g year:2017
|g number:3
|g day:15
|g month:03
|g pages:486-500
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2016.2552172
|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 39
|j 2017
|e 3
|b 15
|c 03
|h 486-500
|