File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Generalized Few-shot Semantic Segmentation

TitleGeneralized Few-shot Semantic Segmentation
Authors
Keywordsgrouping and shape analysis
Representation learning
Segmentation
Issue Date2022
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2022, v. 2022-June, p. 11553-11562 How to Cite?
AbstractTraining semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few- Shot Segmentation (FS-Seg) tackles this problem with many constraints. In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS- Seg), to analyze the generalization ability of simultaneously segmenting the novel categories with very few examples and the base categories with sufficient examples. It is the first study showing that previous representative state-of-the-art FS-Seg methods fall short in GFS-Seg and the performance discrepancy mainly comes from the constrained setting of FS-Seg. To make GFS-Seg tractable, we set up a GFS-Seg baseline that achieves decent performance without structural change on the original model. Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image. Both two contributions are experimentally manifested for their substantial practical merit. Extensive experiments on Pascal-Voc and COCO also show that CAPL generalizes well to FS-Seg by achieving competitive performance. Code is available at https://github.com/dvlab-research/GFS-Seg.
Persistent Identifierhttp://hdl.handle.net/10722/333562
ISSN
2023 SCImago Journal Rankings: 10.331
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorTian, Zhuotao-
dc.contributor.authorLai, Xin-
dc.contributor.authorJiang, Li-
dc.contributor.authorLiu, Shu-
dc.contributor.authorShu, Michelle-
dc.contributor.authorZhao, Hengshuang-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2023-10-06T05:20:36Z-
dc.date.available2023-10-06T05:20:36Z-
dc.date.issued2022-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2022, v. 2022-June, p. 11553-11562-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/333562-
dc.description.abstractTraining semantic segmentation models requires a large amount of finely annotated data, making it hard to quickly adapt to novel classes not satisfying this condition. Few- Shot Segmentation (FS-Seg) tackles this problem with many constraints. In this paper, we introduce a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS- Seg), to analyze the generalization ability of simultaneously segmenting the novel categories with very few examples and the base categories with sufficient examples. It is the first study showing that previous representative state-of-the-art FS-Seg methods fall short in GFS-Seg and the performance discrepancy mainly comes from the constrained setting of FS-Seg. To make GFS-Seg tractable, we set up a GFS-Seg baseline that achieves decent performance without structural change on the original model. Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image. Both two contributions are experimentally manifested for their substantial practical merit. Extensive experiments on Pascal-Voc and COCO also show that CAPL generalizes well to FS-Seg by achieving competitive performance. Code is available at https://github.com/dvlab-research/GFS-Seg.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.subjectgrouping and shape analysis-
dc.subjectRepresentation learning-
dc.subjectSegmentation-
dc.titleGeneralized Few-shot Semantic Segmentation-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR52688.2022.01127-
dc.identifier.scopuseid_2-s2.0-85140072080-
dc.identifier.volume2022-June-
dc.identifier.spage11553-
dc.identifier.epage11562-
dc.identifier.isiWOS:000870759104063-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats