Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation
Weakly supervised semantic instance segmentation with only image-level supervision, instead of relying on expensive pixel-wise masks or bounding box annotations, is an important problem to alleviate the data-hungry nature of deep learning. In this article, we tackle this challenging problem by aggre...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 3 vom: 03. März, Seite 1415-1428
|
|---|
| 1. Verfasser: |
Liu, Yun
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Wu, Yu-Huan,
Wen, Peisong,
Shi, Yujun,
Qiu, Yu,
Cheng, Ming-Ming |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|