Graphonomy : Universal Image Parsing via Graph Reasoning and Transfer
Prior highly-tuned image parsing models are usually studied in a certain domain with a specific set of semantic labels and can hardly be adapted into other scenarios (e.g.sharing discrepant label granularity) without extensive re-training. Learning a single universal parsing model by unifying label...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 5 vom: 01. Mai, Seite 2504-2518
|
|---|
| 1. Verfasser: |
Lin, Liang
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Gao, Yiming,
Gong, Ke,
Wang, Meng,
Liang, Xiaodan |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|