Prior Guided Feature Enrichment Network for Few-Shot Segmentation

Prior Guided Feature Enrichment Network for Few-Shot Segmentation

State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled suppor...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 2 vom: 15. Feb., Seite 1050-1065
1. Verfasser: Tian, Zhuotao (VerfasserIn)
Weitere Verfasser: Zhao, Hengshuang, Shu, Michelle, Yang, Zhicheng, Li, Ruiyu, Jia, Jiaya
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM313260834
003 DE-627
005 20250227173842.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2020.3013717  |2 doi 
028 5 2 |a pubmed25n1044.xml 
035 |a (DE-627)NLM313260834 
035 |a (NLM)32750843 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Tian, Zhuotao  |e verfasserin  |4 aut 
245 1 0 |a Prior Guided Feature Enrichment Network for Few-Shot Segmentation 
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 Revised 10.01.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information of training classes and spatial inconsistency between query and support targets. To alleviate these issues, we propose the Prior Guided Feature Enrichment Network (PFENet). It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks. Extensive experiments on PASCAL-5 i and COCO prove that the proposed prior generation method and FEM both improve the baseline method significantly. Our PFENet also outperforms state-of-the-art methods by a large margin without efficiency loss. It is surprising that our model even generalizes to cases without labeled support samples 
650 4 |a Journal Article 
700 1 |a Zhao, Hengshuang  |e verfasserin  |4 aut 
700 1 |a Shu, Michelle  |e verfasserin  |4 aut 
700 1 |a Yang, Zhicheng  |e verfasserin  |4 aut 
700 1 |a Li, Ruiyu  |e verfasserin  |4 aut 
700 1 |a Jia, Jiaya  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 44(2022), 2 vom: 15. Feb., Seite 1050-1065  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:44  |g year:2022  |g number:2  |g day:15  |g month:02  |g pages:1050-1065 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2020.3013717  |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 2  |b 15  |c 02  |h 1050-1065