Focusing on Valid Search Space in Open-World Compositional Zero-Shot Learning by Leveraging Misleading Answers
The goal of Compositional Zero-Shot Learning (CZSL) is to recognize various compositions of state-object pairs. Because the compositions that need to be considered are only a subset of all combinations of states and objects, it is tough for models to predict unseen compositions. Previous work overlo...
Bewaard in:
| Hoofdauteurs: | , , |
|---|---|
| Formaat: | Artigo |
| Taal: | Inglês |
| Gepubliceerd in: |
IEEE
2024-01-01
|
| Reeks: | IEEE Access |
| Onderwerpen: | |
| Online toegang: | https://ieeexplore.ieee.org/document/10742371/ |
| Tags: |
Geen labels, Wees de eerste die dit record labelt!
|
