Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation

Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, th...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 40(2018), 6 vom: 14. Juni, Seite 1382-1396
1. Verfasser: Saleh, Fatemeh Sadat (VerfasserIn)
Weitere Verfasser: Aliakbarian, Mohammad Sadegh, Salzmann, Mathieu, Petersson, Lars, Alvarez, Jose M, Gould, Stephen
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2018
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM272922536
003 DE-627
005 20231224235922.0
007 cr uuu---uuuuu
008 231224s2018 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2017.2713785  |2 doi 
028 5 2 |a pubmed24n0909.xml 
035 |a (DE-627)NLM272922536 
035 |a (NLM)28613162 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Saleh, Fatemeh Sadat  |e verfasserin  |4 aut 
245 1 0 |a Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation 
264 1 |c 2018 
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 04.04.2019 
500 |a Date Revised 04.04.2019 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using image tags. Without additional information, this leads to poor localization accuracy. This problem, however, was alleviated by making use of objectness priors to generate foreground/background masks. Unfortunately these priors either require pixel-level annotations/bounding boxes, or still yield inaccurate object boundaries. Here, we propose a novel method to extract accurate masks from networks pre-trained for the task of object recognition, thus forgoing external objectness modules. We first show how foreground/background masks can be obtained from the activations of higher-level convolutional layers of a network. We then show how to obtain multi-class masks by the fusion of foreground/background ones with information extracted from a weakly-supervised localization network. Our experiments evidence that exploiting these masks in conjunction with a weakly-supervised training loss yields state-of-the-art tag-based weakly-supervised semantic segmentation results 
650 4 |a Journal Article 
700 1 |a Aliakbarian, Mohammad Sadegh  |e verfasserin  |4 aut 
700 1 |a Salzmann, Mathieu  |e verfasserin  |4 aut 
700 1 |a Petersson, Lars  |e verfasserin  |4 aut 
700 1 |a Alvarez, Jose M  |e verfasserin  |4 aut 
700 1 |a Gould, Stephen  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 40(2018), 6 vom: 14. Juni, Seite 1382-1396  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:40  |g year:2018  |g number:6  |g day:14  |g month:06  |g pages:1382-1396 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2017.2713785  |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 40  |j 2018  |e 6  |b 14  |c 06  |h 1382-1396