Unfreezing the patch embedding during low-rank adaptation of a vision transformer yields 96.35% accuracy on encrypted CIFAR-10 with 0.71M trainable parameters.
Domain adaptation for efficiently fine-tuning vision transformer with encrypted images,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification
Unfreezing the patch embedding during low-rank adaptation of a vision transformer yields 96.35% accuracy on encrypted CIFAR-10 with 0.71M trainable parameters.