Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e., they perform poorly when they are required to incrementally update their m...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 12 vom: 09. Dez., Seite 10099-10113
|
|---|
| 1. Verfasser: |
Cermelli, Fabio
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Mancini, Massimiliano,
Bulo, Samuel Rota,
Ricci, Elisa,
Caputo, Barbara |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|