Few-Shot Class-Incremental Learning with Prompt Alignment and Subspace Prototype Aggregation
Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes with only a few samples, making it more challenging than traditional Class-Incremental Learning (CIL) due to the scarcity of available samples. The imbalance in sample distribution further complicates balancing the abundant base d...
Shranjeno v:
| Glavni avtor: | |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
MDPI AG
2026-05-01
|
| Serija: | Algorithms |
| Teme: | |
| Online dostop: | https://www.mdpi.com/1999-4893/19/5/407 |
| Oznake: |
Brez oznak, prvi označite!
|