Fine-tuning a pretrained vision model with only 2-6% of its LoRA adapters active preserves zero-shot and out-of-distribution performance while matching full-rank LoRA accuracy.
Food-101 - mining discriminative components with random forests
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation
Fine-tuning a pretrained vision model with only 2-6% of its LoRA adapters active preserves zero-shot and out-of-distribution performance while matching full-rank LoRA accuracy.