Learning Good Features to Transfer Across Tasks and Domains
Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests that there should be a way of reusing the knowledge learned...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 8 vom: 06. Aug., Seite 9981-9995
|
1. Verfasser: |
Ramirez, Pierluigi Zama
(VerfasserIn) |
Weitere Verfasser: |
Cardace, Adriano,
De Luigi, Luca,
Tonioni, Alessio,
Salti, Samuele,
Stefano, Luigi Di |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2023
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
Schlagworte: | Journal Article |