Online Attention Accumulation for Weakly Supervised Semantic Segmentation
Object attention maps generated by image classifiers are usually used as priors for weakly supervised semantic segmentation. However, attention maps usually locate the most discriminative object parts. The lack of integral object localization maps heavily limits the performance of weakly supervised...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 10 vom: 25. Okt., Seite 7062-7077
|
|---|
| 1. Verfasser: |
Jiang, Peng-Tao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Han, Ling-Hao,
Hou, Qibin,
Cheng, Ming-Ming,
Wei, Yunchao |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|