Single-stage Semantic Segmentation from Image Labels
| datacite.relation.isDescribedBy | https://arxiv.org/abs/2005.08104 | |
| dc.contributor.advisor | ||
| dc.contributor.author | Araslanov, Nikita | |
| dc.contributor.author | Roth, Stefan | |
| dc.date.accessioned | 2021-12-22T11:09:34Z | |
| dc.date.available | 2021-12-22T11:09:34Z | |
| dc.date.created | 2020-06 | |
| dc.date.issued | 2021-12-22 | |
| dc.description | Recent 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.identifier.uri | https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/3367 | |
| dc.language.iso | en | de_DE |
| dc.rights.license | Apache-2.0 (https://www.apache.org/licenses/LICENSE-2.0) | |
| dc.subject | weak supervision | de_DE |
| dc.subject | semantic segmentation | de_DE |
| dc.subject.classification | 4.43-04 | |
| dc.subject.classification | 4.43-05 | |
| dc.subject.ddc | 004 | |
| dc.title | Single-stage Semantic Segmentation from Image Labels | de_DE |
| dc.type | Software | de_DE |
| dcterms.accessRights | openAccess | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| tuda.history.classification | Version=2016-2020;409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierung | |
| tuda.unit | TUDa |