AFA combines a contrastively trained shared LoRA adapter (AFFA) with an expanding multi-head LoRA mixture-of-experts (ABFA) to enable continual learning of CLIP while slightly improving its zero-shot transfer.
Learning without mem- orizing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models
AFA combines a contrastively trained shared LoRA adapter (AFFA) with an expanding multi-head LoRA mixture-of-experts (ABFA) to enable continual learning of CLIP while slightly improving its zero-shot transfer.