Show simple item record

dc.contributor.authorAraslanov, Nikita
dc.contributor.authorRoth, Stefan
dc.date.accessioned2021-12-22T11:09:34Z
dc.date.available2021-12-22T11:09:34Z
dc.date.issued2020-06
dc.identifier.urihttps://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3367
dc.descriptionRecent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of increased model complexity and sophisticated multi-stage training procedures. This is in contrast to earlier work that used only a single stage − training one segmentation network on image labels − which was abandoned due to inferior segmentation accuracy. In this work, we first define three desirable properties of a weakly supervised method: local consistency, semantic fidelity, and completeness. Using these properties as guidelines, we then develop a segmentation-based network model and a self-supervised training scheme to train for semantic masks from image-level annotations in a single stage. We show that despite its simplicity, our method achieves results that are competitive with significantly more complex pipelines, substantially outperforming earlier single-stage methods.de_DE
dc.language.isoende_DE
dc.relationIsDescribedBy;arXiv;2005.08104
dc.rightsApache License 2.0
dc.rights.urihttps://www.apache.org/licenses/LICENSE-2.0
dc.subjectweak supervisionde_DE
dc.subjectsemantic segmentationde_DE
dc.subject.classification409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierungde_DE
dc.subject.ddc004
dc.titleSingle-stage Semantic Segmentation from Image Labelsde_DE
dc.typeSoftwarede_DE
tud.unitTUDa


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Apache License 2.0
Except where otherwise noted, this item's license is described as Apache License 2.0