Incrementally Learned Angular Representations for Few-Shot Class-Incremental Learning
The main challenge of FSCIL is the trade-off between underfitting to a new session task and preventing forgetting the knowledge for earlier sessions. In this paper, we reveal that the angular space occupied by the features within the embedded area is relatively narrow. Consequently, after the base s...
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
IEEE
2023-01-01
|
| Serie: | IEEE Access |
| Soggetti: | |
| Accesso online: | https://ieeexplore.ieee.org/document/10353956/ |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|